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

    Neuronpedia

    INDEX
    Explanations

    Emojis and varied language content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.72
     the
    0.66
     to
    0.61
     an
    0.60
     or
    0.59
     resistors
    0.58
     a
    0.57
     erythrocytes
    0.56
     rectangles
    0.56
     intravenously
    0.56
    POSITIVE LOGITS
    ো
    0.60
     maravilh
    0.59
    在于
    0.57
    ो
    0.55
    و
    0.55
    ى
    0.55
    dır
    0.54
    わりに
    0.54
    quele
    0.54
    gwood
    0.53
    Act Density 0.000%

    No Known Activations