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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    従
    -0.07
    _dice
    -0.07
    orse
    -0.06
     =================================================
    -0.06
    Initializer
    -0.06
     judged
    -0.06
    мещ
    -0.06
    可以
    -0.06
     ओवर
    -0.06
    有
    -0.06
    POSITIVE LOGITS
    aguay
    0.08
    _sort
    0.06
    .proc
    0.06
    athy
    0.06
    .Fprintf
    0.06
     Everest
    0.06
    ccion
    0.06
     identifiers
    0.06
     UserType
    0.06
     Проф
    0.06
    Act Density 0.037%

    No Known Activations