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

    Neuronpedia

    INDEX
    Explanations

    physical needs and assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     questo
    0.49
    смотрите
    0.49
     queste
    0.48
     situazioni
    0.48
     objRequest
    0.47
     süreç
    0.47
    𝘁
    0.46
     ситуация
    0.46
     этом
    0.46
     ситуации
    0.45
    POSITIVE LOGITS
    A
    0.50
    AN
    0.49
    6
    0.49
    ，
    0.46
    ad
    0.45
    :
    0.45
    4
    0.44
     他
    0.42
     galore
    0.41
    F
    0.41
    Act Density 0.162%

    No Known Activations