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

    Neuronpedia

    INDEX
    Explanations

    code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :m
    -0.08
    ователь
    -0.08
     гост
    -0.08
    <<
    -0.08
     shutters
    -0.07
     megfelelő
    -0.07
     Ladder
    -0.07
     ארבע
    -0.07
     ladder
    -0.07
     corres
    -0.07
    POSITIVE LOGITS
    _HEADERS
    0.08
    raad
    0.08
     personenbez
    0.08
    .digital
    0.07
    (frame
    0.07
    (r
    0.07
    (UUID
    0.07
     copyrighted
    0.07
    ra
    0.07
     repeated
    0.07
    Act Density 0.013%

    No Known Activations