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

    Neuronpedia

    INDEX
    Explanations

    Medication/supplement instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Number
    -0.08
     BF
    -0.07
    -server
    -0.07
    ennifer
    -0.07
     militant
    -0.06
     Destination
    -0.06
     anger
    -0.06
    mpar
    -0.06
     Deniz
    -0.06
     výj
    -0.06
    POSITIVE LOGITS
    	gen
    0.07
     asiat
    0.06
    paque
    0.06
    сім
    0.06
     yardımcı
    0.06
    (image
    0.06
    	expected
    0.06
    vatel
    0.06
     px
    0.06
    आई
    0.06
    Act Density 0.011%

    No Known Activations