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

    Neuronpedia

    INDEX
    Explanations

    Server configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	FOR
    -0.07
    	tp
    -0.07
    -0.06
    	W
    -0.06
    .Condition
    -0.06
     Worksheets
    -0.06
     стратег
    -0.06
    POSITE
    -0.06
    ARRAY
    -0.06
    	fields
    -0.06
    POSITIVE LOGITS
    _human
    0.07
     gelenek
    0.06
    당
    0.06
     dve
    0.06
    estli
    0.06
     Healthy
    0.06
     전국
    0.06
    ensual
    0.06
     hứ
    0.06
     дальней
    0.06
    Act Density 0.019%

    No Known Activations