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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Font
    -0.07
     iyi
    -0.06
    ^^^^
    -0.06
    33
    -0.06
    -gr
    -0.06
     awesome
    -0.06
    ğına
    -0.06
    站
    -0.06
    cest
    -0.06
    allocation
    -0.06
    POSITIVE LOGITS
    _JOIN
    0.06
     Hamas
    0.06
     Uran
    0.06
     речі
    0.06
     rapp
    0.06
     رأ
    0.06
    !»
    0.06
    .ShowDialog
    0.06
    (InitializedTypeInfo
    0.06
    続
    0.06
    Act Density 0.028%

    No Known Activations