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

    Neuronpedia

    INDEX
    Explanations

    concepts related to emotional or psychological struggles and self-awareness

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correctly
    -0.36
    correctly
    -0.36
     calientes
    -0.34
     volantes
    -0.34
    ダス
    -0.34
     человеком
    -0.33
     poil
    -0.33
     seda
    -0.33
    成功
    -0.32
    𓃵
    -0.32
    POSITIVE LOGITS
    UserScript
    0.51
    TagMode
    0.51
    новниш
    0.50
     silenzio
    0.47
    |};
    0.47
     gră
    0.47
    dule
    0.46
     Оно
    0.46
    <0xC9>
    0.45
    lump
    0.45
    Act Density 0.028%

    No Known Activations