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

    Neuronpedia

    INDEX
    Explanations

    view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autor
    -0.06
    endar
    -0.06
     calibration
    -0.06
    calcul
    -0.06
     MAK
    -0.06
     composer
    -0.06
     legends
    -0.06
     scream
    -0.06
    malloc
    -0.06
     Clown
    -0.06
    POSITIVE LOGITS
    ební
    0.07
    ?key
    0.07
    ('~
    0.07
    _IP
    0.07
    кої
    0.07
     lobbyist
    0.07
    Để
    0.07
     miễn
    0.06
     Dmitry
    0.06
    Mary
    0.06
    Act Density 0.006%

    No Known Activations