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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outright
    -0.07
    _nth
    -0.07
     sla
    -0.07
    劭
    -0.07
    ATTR
    -0.07
    胳膊
    -0.07
    яти
    -0.07
     colore
    -0.07
    اتحاد
    -0.07
    	Name
    -0.06
    POSITIVE LOGITS
    മ
    0.08
    =logging
    0.07
    оп
    0.07
     للت
    0.07
    氨酸
    0.07
    ickers
    0.06
    เก
    0.06
    ycled
    0.06
    藉
    0.06
    HER
    0.06
    Act Density 0.001%

    No Known Activations