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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Simple
    -0.06
    .dev
    -0.06
    -only
    -0.06
    /Button
    -0.06
    /simple
    -0.06
     adaptable
    -0.06
     Trad
    -0.06
    orelease
    -0.06
    Draw
    -0.06
    Inset
    -0.06
    POSITIVE LOGITS
    Calculator
    0.06
     Barr
    0.06
     xứ
    0.06
    カード
    0.06
    شه
    0.06
    荒
    0.06
     Terminator
    0.06
    ủa
    0.06
     posicion
    0.06
     Giải
    0.06
    Act Density 0.006%

    No Known Activations