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

    Neuronpedia

    INDEX
    Explanations

    box-shadow:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🔥🔥
    0.88
    derm
    0.86
    volence
    0.86
     lửa
    0.82
     اعظم
    0.80
     insure
    0.79
    ногда
    0.79
     keuntungan
    0.79
     Expedia
    0.78
     BrowserRouter
    0.76
    POSITIVE LOGITS
    ात
    1.11
    ्स
    1.04
    ра
    1.00
    ק
    0.98
    би
    0.95
    ни
    0.92
    ί
    0.92
    па
    0.89
    к
    0.88
    ు
    0.88
    Act Density 0.000%

    No Known Activations