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

    Neuronpedia

    INDEX
    Explanations

    URLs and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     પ્ર
    0.41
    Asked
    0.40
    )){
    0.38
    FISH
    0.37
     prépuce
    0.37
     dit
    0.36
     уж
    0.36
     př
    0.36
    otrich
    0.36
    Farland
    0.35
    POSITIVE LOGITS
     Qxb
    0.45
     NAB
    0.41
    льных
    0.40
    сками
    0.40
     ரா
    0.38
     зарабаты
    0.38
     }^{[
    0.38
    อบ
    0.37
     sech
    0.37
     PIB
    0.36
    Act Density 0.074%

    No Known Activations