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

    Neuronpedia

    INDEX
    Explanations

    Plugin interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ে
    0.49
    枪
    0.48
    球队
    0.48
    یہ
    0.48
    ي
    0.48
    <0x80>
    0.47
    創作
    0.47
    所有
    0.46
     UNITS
    0.46
     nf
    0.45
    POSITIVE LOGITS
    ubin
    0.50
    ot
    0.49
    hte
    0.48
    pe
    0.47
    barrel
    0.47
    iseur
    0.46
    quire
    0.46
    olique
    0.46
    remos
    0.46
     கொடு
    0.46
    Act Density 0.002%

    No Known Activations