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

    Neuronpedia

    INDEX
    Explanations

    varied text and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATUS
    -0.07
    secondary
    -0.06
     congressman
    -0.06
     hurting
    -0.06
    azı
    -0.06
    method
    -0.06
    _CONSTANT
    -0.06
     쿠
    -0.06
     farther
    -0.06
    Iterations
    -0.06
    POSITIVE LOGITS
    ('.
    0.07
     Vậy
    0.07
     dereg
    0.06
     бра
    0.06
    ellungen
    0.06
    (Config
    0.06
    ">'.
    0.06
    /email
    0.06
     fires
    0.06
     на
    0.06
    Act Density 0.000%

    No Known Activations