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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (filter
    -0.07
    Auto
    -0.07
     автомати
    -0.06
     Bloomberg
    -0.06
     Monad
    -0.06
     Spect
    -0.06
    ους
    -0.06
    Phones
    -0.06
     пользователя
    -0.06
     enables
    -0.06
    POSITIVE LOGITS
     없었
    0.06
    ierrez
    0.06
     лиш
    0.06
    ogie
    0.06
    (todo
    0.06
    illator
    0.06
    лати
    0.06
     Οικο
    0.06
    titre
    0.05
     Milli
    0.05
    Act Density 0.020%

    No Known Activations