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

    Neuronpedia

    INDEX
    Explanations

    username

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     currentLocation
    0.58
     Gabriella
    0.57
     Gabriel
    0.57
     marginBottom
    0.57
     Cig
    0.56
    হান
    0.56
     Yamada
    0.56
     Yokohama
    0.55
     Jessica
    0.55
    状態で
    0.55
    POSITIVE LOGITS
     شادی
    0.66
    PATHS
    0.64
    Normalization
    0.59
     phleg
    0.59
     carts
    0.57
     ক্লে
    0.56
    Solid
    0.56
    walking
    0.56
     persuasion
    0.55
    Incrementor
    0.55
    Act Density 0.001%

    No Known Activations