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

    Neuronpedia

    INDEX
    Explanations

    references to legal statements and testimonies

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

    statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    logo
    -0.43
    cols
    -0.43
     promise
    -0.42
     VOTE
    -0.42
     team
    -0.42
    İstin
    -0.42
     vote
    -0.41
    ensatz
    -0.41
    Dims
    -0.41
    கம்
    -0.40
    POSITIVE LOGITS
     statements
    0.97
     Statements
    0.75
     expressions
    0.72
    Statements
    0.71
    statements
    0.70
     messages
    0.69
     STATEMENTS
    0.68
     utterances
    0.67
     sentences
    0.65
     descriptions
    0.63
    Act Density 0.028%

    No Known Activations