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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‘
    -0.08
     allocating
    -0.07
    .updateDynamic
    -0.07
    .FETCH
    -0.07
     młod
    -0.07
    >If
    -0.07
    packed
    -0.06
    .messages
    -0.06
     engulf
    -0.06
     dünyanın
    -0.06
    POSITIVE LOGITS
     Quad
    0.07
     Railroad
    0.07
    𝐧
    0.07
     reliable
    0.07
    楼
    0.07
     Ford
    0.07
     waitress
    0.07
    ibilidad
    0.07
    ancements
    0.07
    ارية
    0.07
    Act Density 0.000%

    No Known Activations