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

    Neuronpedia

    INDEX
    Explanations

    FOR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sign
    -0.07
    IMAL
    -0.06
     Salad
    -0.06
     Autism
    -0.06
    	boost
    -0.06
    Owners
    -0.06
    XT
    -0.06
     Owners
    -0.06
    Peak
    -0.06
     sensors
    -0.06
    POSITIVE LOGITS
     CGContext
    0.07
    堂
    0.07
    .removeFrom
    0.06
    ،↵
    0.06
    ",↵
    0.06
     istih
    0.06
     χρησιμοποι
    0.06
     Tata
    0.06
    Cfg
    0.06
    $f
    0.06
    Act Density 0.002%

    No Known Activations