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

    Neuronpedia

    INDEX
    Explanations

    32

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VERBOSE
    -0.07
    カテ
    -0.07
    asını
    -0.06
     diary
    -0.06
    licence
    -0.06
     kardeş
    -0.06
    FA
    -0.06
    ayıp
    -0.06
     쉬
    -0.06
     Düny
    -0.06
    POSITIVE LOGITS
    (cr
    0.07
    ilinx
    0.07
    .isOpen
    0.07
     landslide
    0.07
    PMC
    0.06
                 ↵
    0.06
    inesis
    0.06
     Kis
    0.06
     Roma
    0.06
    ма
    0.06
    Act Density 0.001%

    No Known Activations