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

    Neuronpedia

    INDEX
    Explanations

    code-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     will
    -0.09
    .defer
    -0.07
     would
    -0.06
    /sdk
    -0.06
    ’ll
    -0.06
    .Inner
    -0.06
    would
    -0.06
    'll
    -0.06
     PX
    -0.06
    Creative
    -0.06
    POSITIVE LOGITS
    اف
    0.07
    츠
    0.07
     compelling
    0.07
    IRM
    0.06
     *)__
    0.06
    apia
    0.06
     normal
    0.06
    ưỡng
    0.06
    edom
    0.06
     giảng
    0.06
    Act Density 3.144%

    No Known Activations