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

    Neuronpedia

    INDEX
    Explanations

    want me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     them
    0.72
    rite
    0.70
    them
    0.69
    കട
    0.69
     pháp
    0.67
     konuda
    0.66
    关于
    0.65
     artist
    0.65
     Those
    0.64
    uthers
    0.63
    POSITIVE LOGITS
     மிகப்பெரிய
    0.82
     hierarchies
    0.81
     tireless
    0.81
     ದೊಡ್ಡ
    0.81
     получает
    0.81
     truncation
    0.80
    <unused523>
    0.79
    CCIÓN
    0.79
     incisions
    0.79
     ನಾವು
    0.78
    Act Density 0.042%

    No Known Activations