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

    Neuronpedia

    INDEX
    Explanations

    output/returned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щение
    -0.08
    علي
    -0.08
    去找
    -0.08
     (('
    -0.08
    ultan
    -0.08
     источник
    -0.08
     copy
    -0.07
    _
    -0.07
     ----------------------------------------------------------------
    -0.07
    ד
    -0.07
    POSITIVE LOGITS
    房貸
    0.07
    (padding
    0.07
    挫折
    0.07
    _NOW
    0.07
    在线角色
    0.06
    锫
    0.06
    حز
    0.06
    limitations
    0.06
     Özel
    0.06
    .fml
    0.06
    Act Density 0.054%

    No Known Activations