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

    Neuronpedia

    INDEX
    Explanations

    case study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंग
    2.06
     gonf
    1.95
    Aw
    1.86
     affluent
    1.84
     awali
    1.82
     sullo
    1.80
    Ath
    1.79
     quê
    1.79
     města
    1.75
    Uw
    1.71
    POSITIVE LOGITS
    ن
    2.72
    ర్
    1.98
    য়
    1.93
    e
    1.89
    אן
    1.88
    ся
    1.77
    মিক্যাল
    1.77
    d
    1.77
     Cases
    1.72
    oning
    1.70
    Act Density 0.038%

    No Known Activations