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

    Neuronpedia

    INDEX
    Explanations

    Frost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	flag
    -0.09
    编号
    -0.08
     Zip
    -0.08
    _flag
    -0.08
    flag
    -0.08
    Zip
    -0.08
    _execute
    -0.08
    zap
    -0.08
     ziliz
    -0.08
    _zip
    -0.08
    POSITIVE LOGITS
     fences
    0.08
     generous
    0.08
     elog
    0.08
     caregiver
    0.08
    riter
    0.08
    0.08
    andising
    0.08
     fence
    0.07
    irme
    0.07
    Автор
    0.07
    Act Density 0.002%
    No Known Activations