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

    Neuronpedia

    INDEX
    Explanations

    reach out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alton
    0.67
     Autob
    0.66
     切り
    0.65
    แข็ง
    0.64
    CTA
    0.64
    CTL
    0.61
     치
    0.61
     Autism
    0.60
    chars
    0.60
    カール
    0.60
    POSITIVE LOGITS
     out
    0.64
    aid
    0.62
     aid
    0.59
    Michel
    0.59
    ora
    0.56
    नेट
    0.56
    sat
    0.55
    out
    0.54
     เลย
    0.54
    เลย
    0.54
    Act Density 0.217%

    No Known Activations