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

    Neuronpedia

    INDEX
    Explanations

    progen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARC
    -0.07
     fondo
    -0.07
    elerle
    -0.06
     Resist
    -0.06
    okrat
    -0.06
    EXP
    -0.06
     chars
    -0.06
     Wars
    -0.06
     말했다
    -0.06
     жир
    -0.06
    POSITIVE LOGITS
     progen
    0.17
    $(
    0.07
     teg
    0.06
     ge
    0.06
     yg
    0.06
    иболее
    0.06
    ạy
    0.06
     Gä
    0.06
    Gen
    0.06
     spanning
    0.06
    Act Density 0.001%

    No Known Activations