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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.98
     THE
    0.92
     Fo
    0.89
     a
    0.86
    Fo
    0.85
     The
    0.81
     safest
    0.81
     Б
    0.79
     Fisk
    0.78
    The
    0.78
    POSITIVE LOGITS
    .(\
    0.77
    .~\
    0.74
    ٌ
    0.71
    ording
    0.70
    .\"
    0.70
    ிடம்
    0.67
    NewDecoder
    0.67
    ($"
    0.67
    .”[
    0.66
    eches
    0.66
    Act Density 0.024%

    No Known Activations