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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     día
    -0.06
    ()?>
    -0.06
     :|:
    -0.06
    손
    -0.06
     Briggs
    -0.06
    xbb
    -0.06
    
    -0.06
    =@"
    -0.06
     losers
    -0.06
     Evening
    -0.06
    POSITIVE LOGITS
    虚
    0.07
    _FIELD
    0.07
     shocked
    0.07
    	menu
    0.06
     erupt
    0.06
     매
    0.06
    comp
    0.06
     comply
    0.06
    [self
    0.06
    icio
    0.06
    Act Density 0.000%

    No Known Activations