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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tries
    -0.07
     RTC
    -0.07
    899
    -0.07
    !',
    -0.06
     подк
    -0.06
     Gravity
    -0.06
     dried
    -0.06
    iska
    -0.06
     victim
    -0.06
     flash
    -0.06
    POSITIVE LOGITS
    による
    0.06
    **/↵↵
    0.06
    页面存档备份
    0.06
    まれ
    0.06
     Hen
    0.06
     Bou
    0.06
     hunt
    0.06
    oj
    0.06
     Abstract
    0.06
    Assign
    0.06
    Act Density 0.012%

    No Known Activations