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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Luc
    -0.08
    وري
    -0.08
    �მ
    -0.08
     lebt
    -0.08
    -0.07
    Luc
    -0.07
    babel
    -0.07
     superb
    -0.07
     ponieważ
    -0.07
    ýun
    -0.07
    POSITIVE LOGITS
     Franchise
    0.09
     franchise
    0.08
    0.08
    [class
    0.07
     franchises
    0.07
    Ị
    0.07
     respectively
    0.07
     dispon
    0.07
    法
    0.07
    தாக
    0.07
    Act Density 0.074%
    No Known Activations