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

    Neuronpedia

    INDEX
    Explanations

    vertical bar and ampersand characters in structured data or text formats

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Demografie
    -0.35
    TestFixture
    -0.32
    ősz
    -0.31
     missione
    -0.30
    jsko
    -0.29
     néz
    -0.29
     ugy
    -0.28
     fué
    -0.28
     perlas
    -0.28
     cuantas
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.69
    хьтан
    0.62
     snippetHide
    0.60
    IndentedString
    0.58
    ConstraintMaker
    0.57
    ِّف
    0.56
    ⟭
    0.56
    fillType
    0.54
     autorytatywna
    0.54
     forState
    0.53
    Act Density 0.017%

    No Known Activations