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

    Neuronpedia

    INDEX
    Explanations

    terms related to diagnostic processes or assessments

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

    diagnostic Instruments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.74
     الرياضيه
    -0.73
    berdayakan
    -0.69
    følge
    -0.69
     okuyayım
    -0.64
     initComponents
    -0.63
     Inscrivez
    -0.63
     metálica
    -0.63
     Theſe
    -0.63
     ſich
    -0.62
    POSITIVE LOGITS
     Pl
    0.43
     Sharp
    0.41
    //
    0.40
     sharp
    0.40
    .*")]
    0.39
     Never
    0.39
     die
    0.38
     Coc
    0.35
     never
    0.35
     Tro
    0.35
    Act Density 0.000%

    No Known Activations