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

    Neuronpedia

    INDEX
    Explanations

    prompts for audience engagement and feedback

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

    invitations to share

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.66
     surla
    -0.65
     IFTT
    -0.63
    uxxxx
    -0.60
    keyColumn
    -0.59
    ToBounds
    -0.59
    featureID
    -0.59
     queſta
    -0.58
    hamshire
    -0.57
    delwed
    -0.57
    POSITIVE LOGITS
     comments
    0.39
     comment
    0.34
     Phil
    0.32
     janela
    0.32
     yorum
    0.31
     share
    0.31
    comments
    0.30
     casar
    0.30
     llena
    0.30
     palabras
    0.30
    Act Density 0.007%

    No Known Activations