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

    Neuronpedia

    INDEX
    Explanations

    abstract noun suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мены
    0.42
     পথে
    0.39
     Khy
    0.39
     discontent
    0.38
     PKR
    0.38
    '`--'`--
    0.38
    ките
    0.37
    avkh
    0.37
    ктак
    0.37
     stayed
    0.37
    POSITIVE LOGITS
    ność
    1.09
    łość
    1.04
    ość
    1.03
    ości
    1.02
    ść
    0.98
    osc
    0.97
    ności
    0.97
    kość
    0.94
    wość
    0.93
    zość
    0.90
    Act Density 0.002%

    No Known Activations