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

    Neuronpedia

    INDEX
    Explanations

    movies and books

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -common
    -0.07
    contracts
    -0.07
    IU
    -0.07
     besides
    -0.06
    arsity
    -0.06
    'nın
    -0.06
     restroom
    -0.06
     mistress
    -0.06
    IDEOS
    -0.06
     fullscreen
    -0.06
    POSITIVE LOGITS
    plementary
    0.06
    �
    0.06
     Coming
    0.06
    $file
    0.06
    Пр
    0.06
     brushes
    0.06
    кость
    0.06
     timed
    0.06
     Absolutely
    0.06
     кол
    0.06
    Act Density 0.040%

    No Known Activations