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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    築
    -0.09
    gia
    -0.08
    -containing
    -0.07
     BUS
    -0.07
     micros
    -0.07
     mixtures
    -0.07
     diaries
    -0.07
     KN
    -0.07
     aged
    -0.07
     Hus
    -0.07
    POSITIVE LOGITS
     applied
    0.10
     bás
    0.09
     sends
    0.09
     aplicado
    0.08
     segíts
    0.08
     essentially
    0.08
     assigns
    0.08
     दिए
    0.08
     avulla
    0.08
     designers
    0.08
    Act Density 0.039%

    No Known Activations