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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [val
    -0.07
     FF
    -0.07
     entities
    -0.07
    _ar
    -0.07
     yards
    -0.06
    (service
    -0.06
     lékař
    -0.06
     enzymes
    -0.06
     переход
    -0.06
     Watson
    -0.06
    POSITIVE LOGITS
    Univers
    0.07
    plusplus
    0.07
    (chart
    0.07
    -toggler
    0.07
    $msg
    0.07
    miş
    0.06
    Indeed
    0.06
    getName
    0.06
    kan
    0.06
     bitter
    0.06
    Act Density 0.027%

    No Known Activations