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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всех
    -0.07
    ってい
    -0.07
    僕
    -0.07
     скры
    -0.07
    یتی
    -0.07
     جن
    -0.07
    .serv
    -0.07
    PTY
    -0.07
    .Collection
    -0.06
     distinct
    -0.06
    POSITIVE LOGITS
     NEO
    0.07
     �
    0.06
     Kasich
    0.06
     fread
    0.05
    eldo
    0.05
     achie
    0.05
     Pearson
    0.05
    />.
    0.05
     Pent
    0.05
     msgid
    0.05
    Act Density 0.027%

    No Known Activations