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

    Neuronpedia

    INDEX
    Explanations

    refer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阳性
    -0.08
    著名的
    -0.08
    +E
    -0.08
     prostate
    -0.08
     attenu
    -0.08
     EA
    -0.08
     Ble
    -0.07
    _UPDATE
    -0.07
     Navy
    -0.07
     insensitive
    -0.07
    POSITIVE LOGITS
    𐌺
    0.08
    切尔
    0.08
    refer
    0.07
    麑
    0.07
    interpreted
    0.07
    儴
    0.07
    🕊
    0.07
    𝓬
    0.07
    ứt
    0.07
    👺
    0.07
    Act Density 0.008%

    No Known Activations