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

    Neuronpedia

    INDEX
    Explanations

    multiple subtopic options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    9
    0.57
     observes
    0.50
    ９
    0.50
    lles
    0.48
    ilst
    0.48
    ラップ
    0.47
    lle
    0.47
    four
    0.46
     JULY
    0.46
    returns
    0.45
    POSITIVE LOGITS
     conhecimento
    0.46
     MDR
    0.46
     articol
    0.45
     Büyük
    0.44
    无论是
    0.44
     Dysfunction
    0.44
    那里
    0.44
     ہوجائیں
    0.43
    setwd
    0.43
     pensamento
    0.42
    Act Density 0.005%

    No Known Activations