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

    Neuronpedia

    INDEX
    Explanations

    multi-language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bigcup
    0.47
    jaz
    0.45
     സന്തോഷ
    0.44
    aworld
    0.44
     inol
    0.44
    last
    0.42
    মৃত্য
    0.42
     जल्द
    0.41
     î
    0.41
     ingresos
    0.41
    POSITIVE LOGITS
     षटके
    0.41
    син
    0.40
    గ్ర
    0.38
    ドラマ
    0.38
     фильме
    0.38
     як
    0.37
     мають
    0.37
     ничек
    0.37
    Як
    0.37
    шают
    0.37
    Act Density 0.047%

    No Known Activations