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

    Neuronpedia

    INDEX
    Explanations

    ma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棪
    -0.07
    according
    -0.07
     ries
    -0.07
    4
    -0.07
     pris
    -0.07
    ippy
    -0.07
    舍得
    -0.07
    angler
    -0.06
    超过了
    -0.06
    ircular
    -0.06
    POSITIVE LOGITS
    ático
    0.07
    _callable
    0.07
    .commons
    0.07
    Download
    0.07
    .getSimpleName
    0.07
     Joint
    0.07
     columna
    0.07
    ка
    0.06
     Motorola
    0.06
     getView
    0.06
    Act Density 0.001%

    No Known Activations