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

    Neuronpedia

    INDEX
    Explanations

    experience with or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     информации
    0.44
    unicaciones
    0.43
     имени
    0.43
    ńskiej
    0.43
    ’
    0.42
    কেশন
    0.42
     очень
    0.41
     их
    0.40
    inį
    0.40
     γλώ
    0.40
    POSITIVE LOGITS
     using
    0.52
    ad
    0.51
    applying
    0.50
     Umgang
    0.50
    p
    0.50
    d
    0.49
     handling
    0.48
     administr
    0.47
    dealing
    0.47
    Using
    0.47
    Act Density 0.023%

    No Known Activations