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

    Neuronpedia

    INDEX
    Explanations

    Emphasis/formatting markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beaux
    -0.09
    踏
    -0.08
    程度
    -0.08
     accommodates
    -0.08
     borrowing
    -0.07
    provided
    -0.07
    -mid
    -0.07
     جميل
    -0.07
    aside
    -0.07
    具
    -0.07
    POSITIVE LOGITS
    Women
    0.09
    Lessons
    0.09
    Unlock
    0.09
     Auswirkungen
    0.08
     developments
    0.08
    Topics
    0.08
    ...”
    0.08
     Acceler
    0.08
    Overview
    0.08
    Effects
    0.08
    Act Density 0.027%

    No Known Activations