Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code-related constructs such as function definitions, assignments, and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Equals signs followed by assignment or method calls

    np_acts-logits-general · gemini-2.0-flash

    assignment or method execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtre
    -0.52
     miſ
    -0.49
     ſen
    -0.48
     UITableViewCell
    -0.44
     ſtill
    -0.43
     ſtate
    -0.43
     Papal
    -0.42
     pleaſure
    -0.42
    かさ
    -0.41
     tranſ
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.98
    RegressionTest
    0.86
    sizeCache
    0.83
    findpost
    0.83
    )_/¯
    0.83
    principalTable
    0.80
     Administrativna
    0.79
     ModelExpression
    0.79
    })));
    0.73
    ContentAsync
    0.70
    Act Density 0.097%

    No Known Activations