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

    Neuronpedia

    INDEX
    Explanations

    html attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ological
    0.65
    Him
    0.65
    Auto
    0.63
    Hmm
    0.61
    Muchas
    0.61
    א
    0.61
    acly
    0.59
    cular
    0.59
    ophthal
    0.59
    Hmmm
    0.59
    POSITIVE LOGITS
     escánd
    0.63
     είναι
    0.61
     Brooklyn
    0.61
     increíble
    0.61
     otoño
    0.60
     Anschließend
    0.59
     arrhythmia
    0.58
    னர்
    0.58
     alerta
    0.58
     sábado
    0.57
    Act Density 0.006%

    No Known Activations