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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to information and suggestions

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

    asking for anything else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.47
    矣
    -0.43
     çoğu
    -0.43
    enterOuterAlt
    -0.41
    toHaveBeen
    -0.39
    IDATE
    -0.39
    Various
    -0.38
    twimg
    -0.38
     disponibilités
    -0.38
    válasz
    -0.38
    POSITIVE LOGITS
     anything
    0.97
     particularly
    0.94
     particolare
    0.94
    particularly
    0.91
     particularmente
    0.90
     besonderen
    0.90
     particolari
    0.89
     besondere
    0.88
     particolarmente
    0.88
     particular
    0.87
    Act Density 0.043%

    No Known Activations