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

    Neuronpedia

    INDEX
    Explanations

    code structure elements, such as brackets and curly braces

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

    Code snippets and code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    keywords and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "!
    -0.57
    (&:
    -0.54
    IsContent
    -0.52
    []
    -0.49
    !",
    -0.48
    :`
    -0.48
    templateUrl
    -0.48
    public
    -0.47
    !”,
    -0.47
    !".
    -0.47
    POSITIVE LOGITS
     if
    1.20
     //
    0.95
     }
    0.94
     }
    0.82
     }\
    0.75
     else
    0.72
     while
    0.70
     foreach
    0.69
     });
    0.68
     اگر
    0.68
    Act Density 0.076%

    No Known Activations