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

    Neuronpedia

    INDEX
    Explanations

    words or hashtags in quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.73
     Кы
    0.72
     J
    0.71
    J
    0.71
     EU
    0.69
    ،
    0.68
     또는
    0.66
     EDITOR
    0.66
     observance
    0.65
     and
    0.64
    POSITIVE LOGITS
    the
    1.05
    𝙖
    0.93
     the
    0.85
    an
    0.79
     lascia
    0.79
    <unused1082>
    0.77
     visites
    0.76
     χρόνια
    0.73
    𝑎
    0.73
     sommeil
    0.72
    Act Density 1.716%

    No Known Activations