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

    Neuronpedia

    INDEX
    Explanations

    win/twin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     golf
    -0.08
     Cookies
    -0.07
    起步
    -0.07
    嗽
    -0.07
    哕
    -0.07
    汲
    -0.07
    首
    -0.07
    STOP
    -0.07
    握手
    -0.07
    _share
    -0.07
    POSITIVE LOGITS
     principle
    0.07
    猪
    0.07
    权限
    0.07
     образом
    0.07
    )`↵
    0.07
    Π
    0.07
     Armen
    0.06
    cią
    0.06
    펶
    0.06
     Springs
    0.06
    Act Density 0.003%

    No Known Activations