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

    Neuronpedia

    INDEX
    Explanations

    random

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _area
    -0.07
    .square
    -0.06
    esz
    -0.06
     Tek
    -0.06
    etect
    -0.06
     Lex
    -0.06
     towns
    -0.06
    stice
    -0.06
     безпеки
    -0.06
    宗
    -0.06
    POSITIVE LOGITS
     random
    0.10
     Random
    0.08
    ********************************
    0.07
     채용
    0.07
    autos
    0.07
    random
    0.07
     rng
    0.07
     randomized
    0.07
    [random
    0.07
     RSS
    0.07
    Act Density 0.025%

    No Known Activations