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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mouse
    -0.07
     Damage
    -0.06
    iseum
    -0.06
    Unix
    -0.06
     Scotch
    -0.06
    gı
    -0.06
     Profession
    -0.06
     Pump
    -0.06
     Sullivan
    -0.06
    -producing
    -0.06
    POSITIVE LOGITS
    $model
    0.07
     halten
    0.07
    월부터
    0.07
    "';
    0.07
     sweetheart
    0.07
    .setView
    0.06
     cesty
    0.06
     ubytování
    0.06
     scipy
    0.06
     heartfelt
    0.06
    Act Density 0.197%

    No Known Activations