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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    厍
    -0.07
    >true
    -0.07
    ሀ
    -0.07
    JPEG
    -0.07
    托运
    -0.07
    .lon
    -0.07
    /mac
    -0.07
    other
    -0.07
    步步
    -0.06
    }];↵
    -0.06
    POSITIVE LOGITS
    actics
    0.08
     filme
    0.07
     Structure
    0.07
    _tau
    0.07
     toute
    0.07
     Tem
    0.07
    Structure
    0.07
     Parenthood
    0.07
     tứ
    0.07
    安然
    0.06
    Act Density 0.070%

    No Known Activations