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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and contrasts

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

    thank you or sorry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ps
    -0.46
    web
    -0.44
    tick
    -0.43
    PasswordField
    -0.43
    cy
    -0.42
    rt
    -0.42
    ich
    -0.42
     בט
    -0.41
    Tom
    -0.40
    ney
    -0.40
    POSITIVE LOGITS
    astéroïdes
    0.60
    elemField
    0.59
    GraphicsUnit
    0.57
     '{@
    0.57
    AddTagHelper
    0.57
     препратки
    0.56
    AutoScaleMode
    0.56
    DeleteBehavior
    0.53
    Explicación
    0.53
     wireType
    0.52
    Act Density 0.213%

    No Known Activations