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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	curl
    -0.07
     ith
    -0.06
    -0.06
    vars
    -0.06
     Вона
    -0.06
     Challenges
    -0.06
     Chatt
    -0.06
     їх
    -0.06
    IBUT
    -0.06
     puis
    -0.06
    POSITIVE LOGITS
     tops
    0.07
     bás
    0.06
    expires
    0.06
     precios
    0.06
     Psychology
    0.06
     Ey
    0.06
    _prediction
    0.06
    StringEncoding
    0.06
     buying
    0.06
    <small
    0.06
    Act Density 0.008%

    No Known Activations