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
    ‑
    -0.08
    -P
    -0.08
    -F
    -0.08
    -style
    -0.08
    -based
    -0.08
     Oval
    -0.08
     avenue
    -0.08
    Peek
    -0.07
    /P
    -0.07
    /E
    -0.07
    POSITIVE LOGITS
     einzelnen
    0.16
     verschiedenen
    0.14
    ציות
    0.13
     siguientes
    0.12
     أسماء
    0.12
     seguintes
    0.12
     הללו
    0.12
    ظمات
    0.12
     विभिन्न
    0.12
     entries
    0.12
    Act Density 0.055%

    No Known Activations