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

    Neuronpedia

    INDEX
    Explanations

    measurements/dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PD
    -0.07
    退市
    -0.07
    ="%
    -0.07
     payouts
    -0.07
    אק
    -0.07
     tph
    -0.07
    .XPath
    -0.06
    />";↵
    -0.06
     mana
    -0.06
    底线
    -0.06
    POSITIVE LOGITS
    ench
    0.07
    日常工作
    0.07
    ㍍
    0.06
     urllib
    0.06
    tréal
    0.06
    _PROC
    0.06
    充足的
    0.06
    處理及
    0.06
    みたい
    0.06
    𝘀
    0.06
    Act Density 0.110%

    No Known Activations