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

    Neuronpedia

    INDEX
    Explanations

    Best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _than
    -0.06
    	day
    -0.06
    ูไ
    -0.06
     Harding
    -0.06
    Startup
    -0.06
     assorted
    -0.06
    阴
    -0.06
     так
    -0.06
    (rect
    -0.06
    áků
    -0.06
    POSITIVE LOGITS
     :";↵
    0.07
     seiz
    0.07
    イト
    0.06
    random
    0.06
    ulse
    0.06
    secs
    0.06
     masturb
    0.06
     genre
    0.06
     site
    0.06
    :");↵
    0.06
    Act Density 0.002%

    No Known Activations