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

    Neuronpedia

    INDEX
    Explanations

    Code/data entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lj
    -0.06
     JB
    -0.06
    (I
    -0.06
    .hl
    -0.06
    <i
    -0.06
    _printer
    -0.06
     TZ
    -0.06
     inhibited
    -0.06
    (PARAM
    -0.06
     indicator
    -0.06
    POSITIVE LOGITS
    usting
    0.07
     qualify
    0.07
    ージ
    0.06
     evitar
    0.06
    สด
    0.06
    омен
    0.06
    YYY
    0.06
    aster
    0.06
    利
    0.06
    建议
    0.06
    Act Density 0.006%

    No Known Activations