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

    Neuronpedia

    INDEX
    Explanations

    exception handling or ignore properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Quarter
    0.45
     apk
    0.42
     yük
    0.41
    ⭒
    0.40
    घड
    0.39
     কাজ
    0.38
    iscid
    0.38
    oksatta
    0.37
     scaler
    0.37
    orthin
    0.37
    POSITIVE LOGITS
    例外
    0.48
     ignor
    0.47
    exceptions
    0.44
    ignores
    0.42
     excepciones
    0.42
    Exception
    0.41
     exceptions
    0.41
     tegas
    0.41
     Pattern
    0.41
     ignoreString
    0.41
    Act Density 0.001%

    No Known Activations