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

    Neuronpedia

    INDEX
    Explanations

    `^`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    0.71
    اب
    0.70
    ي
    0.69
    اه
    0.63
    ır
    0.59
    و
    0.55
    скус
    0.55
    ба
    0.54
    ت
    0.54
    ଈ
    0.54
    POSITIVE LOGITS
    ad
    0.57
     (
    0.56
    ine
    0.55
    ↵
    0.55
     Ivory
    0.54
    ↵↵
    0.54
    att
    0.53
     Residence
    0.52
     Indicates
    0.51
    wind
    0.50
    Act Density 0.020%

    No Known Activations