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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Juli
    -0.07
     thrott
    -0.06
    ìn
    -0.06
    cooldown
    -0.06
     Gordon
    -0.06
    IELD
    -0.06
     ARISING
    -0.06
     Özel
    -0.06
     Horde
    -0.06
     Modern
    -0.06
    POSITIVE LOGITS
    /kubernetes
    0.07
    dfs
    0.06
     Caller
    0.06
    过来
    0.06
     Ск
    0.06
    к
    0.06
    コン
    0.06
    /facebook
    0.06
    (Display
    0.06
    Rock
    0.06
    Act Density 0.019%

    No Known Activations