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

    Neuronpedia

    INDEX
    Explanations

    recently

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	↵	↵	↵	↵
    -0.08
    In
    -0.06
     coined
    -0.06
     rare
    -0.06
     않습니다
    -0.06
    ISK
    -0.06
     rolling
    -0.06
    xCF
    -0.06
     Stats
    -0.06
     FileInputStream
    -0.06
    POSITIVE LOGITS
    *'
    0.09
    	Gtk
    0.08
    אנחנו
    0.08
    friend
    0.07
     stations
    0.07
     iphone
    0.07
    _"
    0.07
     queries
    0.07
    ∴
    0.07
    -pos
    0.07
    Act Density 0.008%

    No Known Activations