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

    Neuronpedia

    INDEX
    Explanations

    Settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    command
    -0.07
    -background
    -0.07
     terminal
    -0.06
     Jah
    -0.06
     introduction
    -0.06
     वजह
    -0.06
     misconception
    -0.06
    -live
    -0.06
    .HandlerFunc
    -0.06
     alphabet
    -0.06
    POSITIVE LOGITS
    rott
    0.07
     vui
    0.07
    (settings
    0.06
    HS
    0.06
    ặt
    0.06
    Ä
    0.06
    ARD
    0.06
    ück
    0.06
    IDDEN
    0.06
     predis
    0.06
    Act Density 0.009%

    No Known Activations