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
     Vend
    -0.08
     vv
    -0.07
    _VALIDATE
    -0.07
    _Val
    -0.07
     wee
    -0.07
    VP
    -0.07
    eller
    -0.07
     gall
    -0.07
    监护
    -0.07
     Gamma
    -0.07
    POSITIVE LOGITS
    大家分享
    0.07
    잦
    0.07
     Auburn
    0.06
    تركيز
    0.06
    避开
    0.06
    ⭞
    0.06
    Traditional
    0.06
    하는데
    0.06
    剧本
    0.06
    razy
    0.06
    Act Density 0.002%

    No Known Activations