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

    Neuronpedia

    INDEX
    Explanations

    language related to controversies and criticism in political contexts

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

    Statements, comments, remarks

    np_acts-logits-general · gemini-2.0-flash

    making statements or comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.58
    __':
    -0.52
    AndroidJUnit
    -0.51
    })->
    -0.50
    ynb
    -0.50
    анд
    -0.49
    assertArray
    -0.49
    vensis
    -0.48
    zeichnis
    -0.48
    ľad
    -0.48
    POSITIVE LOGITS
     statements
    2.13
     statement
    1.94
     remarks
    1.86
     comments
    1.82
     Statements
    1.77
    statements
    1.74
    Statements
    1.63
     comment
    1.60
    statement
    1.59
     remark
    1.58
    Act Density 0.637%

    No Known Activations