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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VG
    -0.08
     Bal
    -0.07
    니스
    -0.07
     kinds
    -0.07
     outlines
    -0.07
     Cake
    -0.07
     paid
    -0.07
     axes
    -0.07
    Effects
    -0.06
    	selected
    -0.06
    POSITIVE LOGITS
    commercial
    0.06
     الإن
    0.06
    σμα
    0.06
     Older
    0.06
     PSI
    0.06
     Tmin
    0.06
     pracovní
    0.06
     Vanity
    0.06
    への
    0.06
    translator
    0.06
    Act Density 0.008%

    No Known Activations