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

    Neuronpedia

    INDEX
    Explanations

    os.path.join

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.50
    ")
    1.41
    ત્
    1.27
    .")
    1.25
    es
    1.22
    و
    1.22
    e
    1.21
    "})
    1.20
    ي
    1.09
     EP
    1.07
    POSITIVE LOGITS
    أ
    1.30
    ídas
    1.23
    ಾಣ
    1.19
    цы
    1.16
    AIN
    1.12
    Pascal
    1.11
    ające
    1.10
    ウド
    1.10
    ẵ
    1.10
    AddModelError
    1.09
    Act Density 0.005%

    No Known Activations