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

    Neuronpedia

    INDEX
    Explanations

    stand-up comedy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    나요
    -0.07
    yme
    -0.07
    eyen
    -0.07
     spirited
    -0.07
    uously
    -0.06
    .translation
    -0.06
    BLEM
    -0.06
    ouv
    -0.06
    ينه
    -0.06
     пенс
    -0.06
    POSITIVE LOGITS
    ao
    0.06
     espect
    0.06
     volta
    0.06
     chatter
    0.06
    (util
    0.06
    */
    0.06
    /classes
    0.06
    ":{"
    0.06
     sessuali
    0.05
     Cascade
    0.05
    Act Density 0.032%

    No Known Activations