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

    Neuronpedia

    INDEX
    Explanations

    azed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verv
    -0.08
    .APP
    -0.07
    słuch
    -0.07
    嘴
    -0.07
     palate
    -0.06
     있어
    -0.06
     technically
    -0.06
     다양한
    -0.06
     wichtig
    -0.06
    只要你
    -0.06
    POSITIVE LOGITS
    يوم
    0.07
    give
    0.07
    いった
    0.07
     rental
    0.07
    碾
    0.07
    敞
    0.07
     predicting
    0.07
     comprised
    0.06
    ^-
    0.06
    听到
    0.06
    Act Density 0.077%

    No Known Activations