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

    Neuronpedia

    INDEX
    Explanations

    implement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	clear
    -0.07
    _P
    -0.07
     Wikimedia
    -0.07
     National
    -0.07
    _L
    -0.06
    欧美
    -0.06
    alan
    -0.06
     oct
    -0.06
    omedical
    -0.06
    climate
    -0.06
    POSITIVE LOGITS
    	cb
    0.07
    linger
    0.06
    CVE
    0.06
    는데
    0.06
    ώσεις
    0.06
    ;m
    0.06
    监听
    0.06
    ekte
    0.06
    (ml
    0.06
    Maker
    0.06
    Act Density 0.019%

    No Known Activations