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

    Neuronpedia

    INDEX
    Explanations

    Code sections

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     Św
    -0.07
    	Collection
    -0.07
    Neo
    -0.07
     Enum
    -0.07
    индив
    -0.07
    -purple
    -0.06
     supp
    -0.06
    UFFIX
    -0.06
     manifestation
    -0.06
     Jaune
    -0.06
    POSITIVE LOGITS
    赛
    0.08
    fit
    0.07
    GS
    0.07
     WebDriverWait
    0.07
    -tracking
    0.07
     hav
    0.07
    has
    0.06
    cancel
    0.06
    _runtime
    0.06
    审核
    0.06
    Act Density 0.010%

    No Known Activations