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

    Neuronpedia

    INDEX
    Explanations

    cosine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _residual
    -0.08
    Ê
    -0.07
    cxx
    -0.07
    ấy
    -0.07
    -al
    -0.07
    💠
    -0.07
    Ret
    -0.07
     nour
    -0.07
    _lib
    -0.07
    拳头
    -0.07
    POSITIVE LOGITS
    ᴶ
    0.07
    粼
    0.07
    _ORD
    0.07
     carved
    0.06
     śl
    0.06
    plätze
    0.06
    ınızı
    0.06
    技术水平
    0.06
    硎
    0.06
    Wh
    0.06
    Act Density 0.002%

    No Known Activations