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

    Neuronpedia

    INDEX
    Explanations

    Python code structure and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    py Results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.77
    TagMode
    -0.71
    IsContent
    -0.69
    OGND
    -0.67
    -0.65
    الإنجليزية
    -0.62
     jspb
    -0.62
    -0.62
    ngths
    -0.62
    Datuak
    -0.61
    POSITIVE LOGITS
     Akhir
    0.36
    RefNanny
    0.34
     Jack
    0.31
     flamme
    0.31
    DispatchQueue
    0.30
     saludos
    0.30
    acka
    0.30
     aplicable
    0.29
    Erstellt
    0.29
    GroupLayout
    0.28
    Act Density 0.002%

    No Known Activations