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

    Neuronpedia

    INDEX
    Explanations

    projectPoints, string conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.82
     the
    0.76
     an
    0.76
     more
    0.74
     you
    0.71
     your
    0.67
     one
    0.64
     we
    0.64
     three
    0.63
     scientists
    0.62
    POSITIVE LOGITS
    Disabled
    0.74
    kowania
    0.73
    ającą
    0.70
    établir
    0.69
    [*][[
    0.69
    Mask
    0.68
    Nếu
    0.67
    NaOMe
    0.65
    cuando
    0.65
    owała
    0.65
    Act Density 0.671%

    No Known Activations