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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reasonably
    -0.07
     site
    -0.07
     corresponds
    -0.07
    FROM
    -0.06
    Добав
    -0.06
    [number
    -0.06
     здоров
    -0.06
    duct
    -0.06
     argument
    -0.06
    ité
    -0.06
    POSITIVE LOGITS
     Xuân
    0.06
     ⟨
    0.06
    IXEL
    0.06
    onders
    0.06
    sss
    0.06
    _UART
    0.06
     รอบ
    0.06
    .flip
    0.06
     Mathf
    0.06
    iếng
    0.06
    Act Density 0.073%

    No Known Activations