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

    Neuronpedia

    INDEX
    Explanations

    defensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     несколь
    -0.07
     Logs
    -0.07
    firm
    -0.07
     yoga
    -0.07
    .album
    -0.07
    าร
    -0.06
    getDefault
    -0.06
     Fall
    -0.06
     当
    -0.06
     Abr
    -0.06
    POSITIVE LOGITS
     slang
    0.07
    chrome
    0.06
     UIView
    0.06
     |--------------------------------------------------------------------------↵
    0.06
    (undefined
    0.06
     Victorian
    0.06
     eerie
    0.06
     coy
    0.06
     ☆
    0.06
     อำ
    0.06
    Act Density 0.005%

    No Known Activations