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

    Neuronpedia

    INDEX
    Explanations

    does/do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дорог
    -0.07
     dich
    -0.07
     lib
    -0.07
     cosas
    -0.07
     名
    -0.07
    -0.06
     Austin
    -0.06
    esda
    -0.06
     tend
    -0.06
     ordin
    -0.06
    POSITIVE LOGITS
     právní
    0.06
    gulp
    0.06
    -с
    0.06
    sthrough
    0.06
     arası
    0.06
    .frequency
    0.06
     zase
    0.06
    ا�
    0.06
     ق
    0.06
    REMOVE
    0.06
    Act Density 0.045%

    No Known Activations