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

    Neuronpedia

    INDEX
    Explanations

    code documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बल्
    0.77
    footnotesize
    0.76
    ália
    0.74
     कोषा
    0.74
    ৃতির
    0.74
     Deserialize
    0.73
    Drama
    0.72
     fonds
    0.71
     fantastic
    0.71
     konu
    0.71
    POSITIVE LOGITS
    $)$.
    0.63
    Ridge
    0.61
    ".
    0.61
    noc
    0.61
    acetic
    0.61
    لها
    0.60
     onc
    0.60
    [&
    0.59
     വിശ്വാ
    0.59
    )_{
    0.59
    Act Density 0.002%

    No Known Activations