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

    Neuronpedia

    INDEX
    Explanations

    contributor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inflicted
    -0.09
    -tra
    -0.07
     Shortly
    -0.07
     adopts
    -0.07
    _dice
    -0.07
    .recipe
    -0.07
     ape
    -0.07
    .Sqrt
    -0.07
    (square
    -0.07
    loe
    -0.07
    POSITIVE LOGITS
    NB
    0.07
     scalability
    0.07
     yearly
    0.07
     Pag
    0.07
    蹇
    0.07
     analog
    0.07
     Compar
    0.06
    Anal
    0.06
    另一方面
    0.06
     굉장
    0.06
    Act Density 0.000%

    No Known Activations