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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هو
    -0.07
    еле
    -0.06
    šší
    -0.06
    _error
    -0.06
    .listeners
    -0.06
     Consultant
    -0.06
     нет
    -0.06
     stitched
    -0.06
     Species
    -0.06
    rotation
    -0.06
    POSITIVE LOGITS
    ****************************************************************
    0.07
    S
    0.07
     Five
    0.07
     Cv
    0.06
     globals
    0.06
     Finding
    0.06
     phrases
    0.06
    Official
    0.06
     mg
    0.06
    (bin
    0.06
    Act Density 0.001%

    No Known Activations