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

    Neuronpedia

    INDEX
    Explanations

    terms and methodologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٖ
    0.40
    scrollHeight
    0.39
    incy
    0.38
    Graham
    0.38
    訓
    0.38
    रल
    0.38
    PHOTOS
    0.38
    туи
    0.38
     Segurança
    0.37
     صدا
    0.36
    POSITIVE LOGITS
    ology
    0.61
    ologías
    0.56
    ologies
    0.56
    ologii
    0.43
    λογία
    0.42
    ोलॉजी
    0.42
    ologija
    0.42
     nop
    0.42
    ኖ
    0.41
    логии
    0.41
    Act Density 0.008%

    No Known Activations