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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extended
    -0.07
    风雨
    -0.07
    _argv
    -0.07
    鞫
    -0.06
    退役
    -0.06
    прод
    -0.06
     Kin
    -0.06
     �
    -0.06
    自動
    -0.06
    .Events
    -0.06
    POSITIVE LOGITS
    rown
    0.07
    手下
    0.07
     offence
    0.07
    regor
    0.07
     Servers
    0.06
    nested
    0.06
    龙泉
    0.06
     Fur
    0.06
     Fortune
    0.06
    sr
    0.06
    Act Density 0.020%

    No Known Activations