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

    Neuronpedia

    INDEX
    Explanations

    formula generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ienen
    -0.08
     segn
    -0.08
    ivities
    -0.08
    enja
    -0.08
    ablemente
    -0.08
     preuves
    -0.07
     التمو
    -0.07
    dw
    -0.07
    ?),
    -0.07
    ittings
    -0.07
    POSITIVE LOGITS
    seat
    0.07
    Seat
    0.07
    ில்
    0.07
     સર
    0.07
    のお
    0.07
     applications
    0.07
     Seat
    0.07
    Seven
    0.07
    guna
    0.07
    arf
    0.07
    Act Density 0.025%

    No Known Activations