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

    Neuronpedia

    INDEX
    Explanations

    naming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     나를
    -0.07
    گیرد
    -0.06
     bottle
    -0.06
     compliments
    -0.06
     изуч
    -0.06
    )의
    -0.06
    _CHK
    -0.06
    _edge
    -0.06
    .Try
    -0.06
    NaN
    -0.06
    POSITIVE LOGITS
     скор
    0.07
     čty
    0.07
    Vel
    0.07
    deal
    0.06
     lij
    0.06
    owego
    0.06
     rigid
    0.06
    Computed
    0.06
     Slider
    0.06
     dwell
    0.06
    Act Density 0.022%

    No Known Activations