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

    Neuronpedia

    INDEX
    Explanations

    model explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Конгрегация
    1.26
     Imágenes
    1.08
     człowieka
    1.05
    $\--
    1.02
     Gó
    1.02
     Sebagai
    1.02
     Arbe
    0.98
     zahlreiche
    0.98
     najwięks
    0.95
     tatsächlich
    0.95
    POSITIVE LOGITS
    га
    1.71
    ない
    1.25
    ig
    1.23
    д
    1.22
    0
    1.17
    ৯
    1.16
    w
    1.13
    ون
    1.12
    er
    1.10
    т
    1.09
    Act Density 1.259%

    No Known Activations