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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आत
    -0.06
    фра
    -0.06
     Für
    -0.06
     DEAD
    -0.06
    жд
    -0.06
    ").↵
    -0.06
     Extra
    -0.06
    ()">↵
    -0.06
     رفته
    -0.06
     activations
    -0.06
    POSITIVE LOGITS
    izontally
    0.07
    ："
    0.06
    /bus
    0.06
    lus
    0.06
     약
    0.06
    acob
    0.06
    .misc
    0.06
    一般
    0.06
     mbedtls
    0.06
     whereabouts
    0.06
    Act Density 0.004%

    No Known Activations