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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PIPE
    -0.08
    #error
    -0.08
    _MAN
    -0.07
     Hàng
    -0.07
    醌
    -0.06
    🍬
    -0.06
    给我们
    -0.06
    InBackground
    -0.06
    見え
    -0.06
    쉰
    -0.06
    POSITIVE LOGITS
     Boolean
    0.07
     Hội
    0.07
    Ḵ
    0.07
     Yale
    0.07
     Birthday
    0.07
     Foot
    0.06
    技法
    0.06
     fooled
    0.06
    heit
    0.06
     strtoupper
    0.06
    Act Density 0.003%

    No Known Activations