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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Damn
    -0.07
     Isl
    -0.07
     dp
    -0.07
     Wander
    -0.07
    Hp
    -0.07
    gMaps
    -0.07
    贝尔
    -0.07
     Bits
    -0.07
    تعب
    -0.07
     plateau
    -0.07
    POSITIVE LOGITS
    ▸
    0.08
    =="
    0.07
    /xhtml
    0.07
    ('-
    0.07
     встреч
    0.07
     deprecated
    0.07
    твор
    0.07
    第三季度
    0.07
    �습니다
    0.07
    internal
    0.06
    Act Density 0.006%

    No Known Activations