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

    Neuronpedia

    INDEX
    Explanations

    Erin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	size
    -0.07
     Wy
    -0.07
     Kh
    -0.06
     bank
    -0.06
     enclosed
    -0.06
    Bruce
    -0.06
    )]
↵
    -0.06
     band
    -0.06
    	msg
    -0.06
    [code
    -0.06
    POSITIVE LOGITS
     Erin
    0.08
     Devon
    0.07
    isten
    0.07
    فاع
    0.07
    osten
    0.07
     Unicorn
    0.07
    editor
    0.07
     McCorm
    0.06
    nické
    0.06
     Gallagher
    0.06
    Act Density 0.002%

    No Known Activations