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

    Neuronpedia

    INDEX
    Explanations

    forward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSDictionary
    -0.07
     pornography
    -0.07
    اورپ
    -0.07
     Living
    -0.06
    [hash
    -0.06
     infertility
    -0.06
     decide
    -0.06
     eliminated
    -0.06
    pections
    -0.06
     Ciudad
    -0.06
    POSITIVE LOGITS
     forward
    0.08
     outspoken
    0.07
    forward
    0.06
    -by
    0.06
    	flex
    0.06
    	duration
    0.06
     EX
    0.06
    WithString
    0.06
    Ultra
    0.06
    	CHECK
    0.06
    Act Density 0.001%

    No Known Activations