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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =end
    -0.09
     Alma
    -0.09
     Compressor
    -0.09
     sag
    -0.08
     yard
    -0.08
    gravity
    -0.08
     میرے
    -0.08
     Compose
    -0.08
     مُ
    -0.08
    idagi
    -0.08
    POSITIVE LOGITS
     మంది
    0.10
     Enumeration
    0.09
     count
    0.08
    投稿
    0.08
    Enumeration
    0.08
     എണ്ണം
    0.08
     tableaux
    0.08
    (Filter
    0.08
     জন
    0.08
    .count
    0.08
    Act Density 0.027%

    No Known Activations