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

    Neuronpedia

    INDEX
    Explanations

    class method rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    씩
    0.78
    umine
    0.77
    <0x92>
    0.77
    iaal
    0.76
    kant
    0.75
    freien
    0.73
    ligare
    0.73
    ierten
    0.72
    poruč
    0.72
    مین
    0.72
    POSITIVE LOGITS
    śmy
    0.92
    檚
    0.84
     acid
    0.82
    est
    0.80
    瞅
    0.79
    抉
    0.79
     ulcer
    0.79
     slike
    0.78
     ozone
    0.77
     oczy
    0.77
    Act Density 0.002%

    No Known Activations