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

    Neuronpedia

    INDEX
    Explanations

    references to people and surnames

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

    programming module names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Johansson
    -0.33
     Smith
    -0.32
     regularmente
    -0.32
    adhyay
    -0.31
     negro
    -0.31
     period
    -0.30
     "
    -0.30
     M
    -0.29
     Williams
    -0.29
     Ferguson
    -0.29
    POSITIVE LOGITS
    Personensuche
    0.74
    GraphicsUnit
    0.73
    AnimationsModule
    0.72
    RectangleBorder
    0.70
     Infórmanos
    0.69
    InitVars
    0.69
    setViewportView
    0.69
    LLocation
    0.69
    MLLoader
    0.69
    InvalidProtocol
    0.69
    Act Density 0.391%

    No Known Activations