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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    di
    -0.07
    ент
    -0.07
    自学
    -0.07
    种类
    -0.07
     Elvis
    -0.07
    设定
    -0.07
    /index
    -0.07
     GOD
    -0.07
    锄
    -0.07
    ovable
    -0.07
    POSITIVE LOGITS
    (condition
    0.08
    rape
    0.06
     להתמוד
    0.06
    rikes
    0.06
    rokes
    0.06
     lleg
    0.06
     egregious
    0.06
    鹴
    0.06
     rencont
    0.06
    ']=="
    0.06
    Act Density 0.007%

    No Known Activations