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

    Neuronpedia

    INDEX
    Explanations

    project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மன
    0.67
     ተመሳሳይ
    0.60
     भग्न
    0.57
     किमान
    0.57
     खोजने
    0.56
     શક્ય
    0.55
     znacznie
    0.55
     ሁለት
    0.55
    pageSize
    0.55
     नंतर
    0.55
    POSITIVE LOGITS
    d
    0.59
    ,
    0.53
    ’
    0.48
    <em>
    0.46
    /
    0.44
    .
    0.43
    :
    0.43
    ges
    0.42
    ება
    0.42
    *
    0.42
    Act Density 0.000%

    No Known Activations