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

    Neuronpedia

    INDEX
    Explanations

    little bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monks
    -0.07
     Walt
    -0.06
    .consume
    -0.06
    utow
    -0.06
     Sox
    -0.06
     Least
    -0.06
    스크
    -0.06
    وفي
    -0.06
    xmm
    -0.06
    सर
    -0.06
    POSITIVE LOGITS
    有点
    0.07
     '^
    0.07
     illuminate
    0.06
    _playlist
    0.06
    确
    0.06
     etwas
    0.06
    розум
    0.06
     anesthesia
    0.06
     filling
    0.06
     conducting
    0.06
    Act Density 0.020%

    No Known Activations