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

    Neuronpedia

    INDEX
    Explanations

    Structured data/lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hands
    -0.08
     bask
    -0.07
    gio
    -0.07
    any
    -0.07
     gerektiğini
    -0.07
     bash
    -0.07
    睁开
    -0.07
    (ch
    -0.07
     Days
    -0.07
    汤
    -0.07
    POSITIVE LOGITS
    Ḋ
    0.07
    "):
↵
    0.07
    ète
    0.07
     chiếu
    0.07
    展演
    0.07
    ﺚ
    0.07
    成功
    0.06
     tín
    0.06
     يؤدي
    0.06
    📽
    0.06
    Act Density 0.121%

    No Known Activations