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

    Neuronpedia

    INDEX
    Explanations

    code, macros

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brah
    -0.08
    -cylinder
    -0.08
     surfer
    -0.08
     polarization
    -0.07
     normalization
    -0.07
     depletion
    -0.07
    .normalize
    -0.07
     Randall
    -0.07
     disagreement
    -0.07
     polarized
    -0.07
    POSITIVE LOGITS
    declare
    0.09
    _enable
    0.09
    _TEST
    0.08
    _REGISTER
    0.08
    akh
    0.08
    (lp
    0.08
     രജ
    0.08
    register
    0.08
    aketa
    0.07
     등록
    0.07
    Act Density 0.002%

    No Known Activations