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

    Neuronpedia

    INDEX
    Explanations

    formal references to organizations and specific entities

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

    discrimination or diversity talk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.53
    principalTable
    -0.50
    IsContent
    -0.48
     HasFactory
    -0.47
    -0.44
    RenderAtEndOf
    -0.43
    kloped
    -0.41
    󠁢
    -0.41
     MainAxisSize
    -0.41
     almuerzo
    -0.40
    POSITIVE LOGITS
    MessageTagHelper
    0.51
    kla
    0.45
     Италијани
    0.44
    Logging
    0.44
    Thank
    0.44
     betweenstory
    0.43
    Cyfeiriadau
    0.43
    Derbyniad
    0.43
    Excellent
    0.42
    Hil
    0.42
    Act Density 0.000%

    No Known Activations