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

    Neuronpedia

    INDEX
    Explanations

    questions and suggestions regarding actions or recommendations

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

    asking what should happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     folha
    -0.46
     prefeitura
    -0.41
     mães
    -0.40
     gärna
    -0.40
     ilman
    -0.37
     clicar
    -0.36
     moldura
    -0.36
     mãe
    -0.36
     coroa
    -0.36
     simplemente
    -0.35
    POSITIVE LOGITS
    vician
    0.71
    ⤹
    0.62
     صوتيه
    0.62
     فريبيس
    0.60
    OGND
    0.56
     Shell
    0.54
     ExecuteAsync
    0.54
    ⟬
    0.54
    eseed
    0.53
    Should
    0.53
    Act Density 0.015%

    No Known Activations