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

    Neuronpedia

    INDEX
    Explanations

    different languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (className
    -0.07
     ECC
    -0.07
    enties
    -0.06
    _offer
    -0.06
    _packet
    -0.06
    Cached
    -0.06
     glaciers
    -0.06
     KDE
    -0.06
     diets
    -0.06
     surprised
    -0.06
    POSITIVE LOGITS
     maj
    0.07
    FirstChild
    0.07
    	EIF
    0.07
     přibliž
    0.06
     tslint
    0.06
     �
    0.06
     Kro
    0.06
     QFont
    0.06
     відом
    0.06
    .espresso
    0.06
    Act Density 0.082%

    No Known Activations