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

    Neuronpedia

    INDEX
    Explanations

    current date/time reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorità
    0.52
     pédicule
    0.45
    罂
    0.43
    辊
    0.43
     enforces
    0.42
    力が
    0.42
     upotre
    0.42
     ответственность
    0.41
    Ⲏ
    0.41
    ᱔
    0.41
    POSITIVE LOGITS
    ert
    0.44
    nb
    0.43
    tail
    0.42
    js
    0.42
    anterior
    0.41
    uma
    0.40
    in
    0.39
    ensity
    0.39
     Georges
    0.38
    int
    0.38
    Act Density 0.005%

    No Known Activations