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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Natur
    -0.07
    _tC
    -0.06
     Asus
    -0.06
    ocabulary
    -0.06
     harsh
    -0.06
    'nın
    -0.06
    Ｋ
    -0.06
    Ａ
    -0.06
     mata
    -0.06
    Calcul
    -0.06
    POSITIVE LOGITS
     Factors
    0.07
     millet
    0.06
    ونا
    0.06
    .Intent
    0.06
     труда
    0.06
    賣
    0.06
    anon
    0.06
     yandan
    0.06
    ève
    0.06
    -facing
    0.06
    Act Density 0.067%

    No Known Activations