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

    Neuronpedia

    INDEX
    Explanations

    25

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fire
    -0.06
    	final
    -0.06
     Advantage
    -0.06
    烧
    -0.06
     đá
    -0.06
    .D
    -0.06
    	RTLR
    -0.06
    Marker
    -0.06
    .Logf
    -0.06
     همین
    -0.06
    POSITIVE LOGITS
     CVE
    0.07
     positioned
    0.07
    unsqueeze
    0.07
     قط
    0.07
     Displays
    0.06
     enorm
    0.06
    險
    0.06
     Inspector
    0.06
    exter
    0.06
    cancel
    0.06
    Act Density 0.015%

    No Known Activations