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

    Neuronpedia

    INDEX
    Explanations

    brake pads and brushes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    も
    0.68
    انی
    0.68
    いた
    0.66
    ری
    0.66
    के
    0.62
    월
    0.62
     کار
    0.61
     شکل
    0.61
    さんに
    0.61
    도
    0.59
    POSITIVE LOGITS
    ang
    0.67
    et
    0.66
     to
    0.66
    s
    0.66
    to
    0.66
    sin
    0.63
    ir
    0.61
    yn
    0.60
    or
    0.60
    頖
    0.59
    Act Density 0.001%

    No Known Activations