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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    objective
    -0.07
     darauf
    -0.07
    죽
    -0.07
     vědom
    -0.07
     Mana
    -0.07
    عن
    -0.06
    ++;↵
    -0.06
     Values
    -0.06
     tog
    -0.06
     warranties
    -0.06
    POSITIVE LOGITS
    ทางการ
    0.07
    .setPrototypeOf
    0.06
     представляет
    0.06
     Biblical
    0.06
     plausible
    0.06
    사회
    0.06
    하는데
    0.06
    へと
    0.06
    ccess
    0.06
     OpenSSL
    0.06
    Act Density 0.032%

    No Known Activations