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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cart
    -0.08
     duyệt
    -0.07
    .RowCount
    -0.06
     Labs
    -0.06
    ايا
    -0.06
     passes
    -0.06
    _subset
    -0.06
    unei
    -0.06
    acteria
    -0.06
     repeating
    -0.06
    POSITIVE LOGITS
     hardness
    0.06
    =F
    0.06
     perd
    0.06
     Sphere
    0.06
     clicks
    0.06
     зобов
    0.06
     convent
    0.06
    	op
    0.06
    啪
    0.06
    green
    0.06
    Act Density 0.197%

    No Known Activations