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

    Neuronpedia

    INDEX
    Explanations

    flag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    比例
    -0.07
     Comfort
    -0.06
    두
    -0.06
    _UNIX
    -0.06
     postseason
    -0.06
     Audrey
    -0.06
    δά
    -0.06
     Čes
    -0.06
     Hal
    -0.06
     circus
    -0.06
    POSITIVE LOGITS
    etched
    0.07
    يان
    0.07
    .agent
    0.06
    rote
    0.06
    inished
    0.06
     vod
    0.06
    :start
    0.06
    :]↵↵
    0.06
    rava
    0.06
    okin
    0.06
    Act Density 0.015%

    No Known Activations