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

    Neuronpedia

    INDEX
    Explanations

    likely to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ುದ
    0.92
    ात्
    0.89
    akim
    0.87
    amag
    0.85
    ালি
    0.84
    motionProxy
    0.83
    larında
    0.82
     phép
    0.81
    ierrez
    0.81
    न
    0.80
    POSITIVE LOGITS
    \(
    0.73
     been
    0.71
    я
    0.69
    いる
    0.62
    ശി
    0.61
    자
    0.61
    ATS
    0.60
    Elig
    0.60
    ս
    0.60
     appearances
    0.59
    Act Density 0.031%

    No Known Activations