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

    Neuronpedia

    INDEX
    Explanations

    as of date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     часть
    0.50
     μέρος
    0.42
     part
    0.41
    Part
    0.38
     Part
    0.38
    part
    0.37
     ಪು
    0.37
     частина
    0.36
     parte
    0.36
     Such
    0.36
    POSITIVE LOGITS
     far
    0.72
     silly
    0.63
     goofy
    0.57
    weird
    0.51
     weird
    0.51
     funny
    0.50
     fascinating
    0.48
     crazy
    0.48
    uming
    0.48
    funny
    0.47
    Act Density 0.028%

    No Known Activations