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

    Neuronpedia

    INDEX
    Explanations

    chime in, pipe up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.08
    IN
    0.91
    ’
    0.85
    dale
    0.84
    y
    0.75
    lerinin
    0.73
    EN
    0.72
    lene
    0.72
    lerle
    0.72
    d
    0.71
    POSITIVE LOGITS
    ش
    0.89
    مين
    0.71
    ير
    0.70
    িয়া
    0.70
    <0x0D>
    0.69
    azes
    0.67
    م
    0.66
    ون
    0.65
    یدی
    0.65
    يل
    0.64
    Act Density 0.000%

    No Known Activations