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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grounds
    -0.08
    吻
    -0.07
     Defines
    -0.07
     Performs
    -0.07
     já
    -0.07
    .imp
    -0.07
     קיש
    -0.07
     navegador
    -0.07
    都能够
    -0.07
     Nhật
    -0.07
    POSITIVE LOGITS
    obsług
    0.07
    _SER
    0.07
    훽
    0.07
    בחר
    0.07
    ≓
    0.07
    닪
    0.06
    นโย
    0.06
    ≋
    0.06
    _CAL
    0.06
     retros
    0.06
    Act Density 0.045%

    No Known Activations