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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vogue
    -0.07
    จอ
    -0.07
    毂
    -0.07
     Indianapolis
    -0.07
    issan
    -0.07
    printf
    -0.07
    旺
    -0.07
    Catch
    -0.07
    ROADCAST
    -0.07
     Fully
    -0.07
    POSITIVE LOGITS
    ᅯ
    0.07
    ゎ
    0.07
    水管
    0.07
    תבר
    0.06
     الأمري
    0.06
     equipos
    0.06
     oblig
    0.06
     EDM
    0.06
    _LOADED
    0.06
     trunc
    0.06
    Act Density 0.012%

    No Known Activations