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

    Neuronpedia

    INDEX
    Explanations

    brain-computer interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    into
    -0.07
    KN
    -0.07
    .Registry
    -0.07
     तह
    -0.07
    )).
    -0.07
    อนด
    -0.06
     Федера
    -0.06
     incompetent
    -0.06
    /book
    -0.06
     Tos
    -0.06
    POSITIVE LOGITS
     ';'
    0.07
     empleado
    0.06
     addr
    0.06
    -purpose
    0.06
     caravan
    0.06
     traveler
    0.06
     persisted
    0.06
     IDR
    0.06
    交通
    0.06
     drown
    0.05
    Act Density 0.017%

    No Known Activations