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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and code structure elements in programming contexts

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

    server configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    package
    -0.46
     kuin
    -0.37
    utuhkan
    -0.35
     elkaar
    -0.35
     הכ
    -0.33
     dulu
    -0.33
     utom
    -0.32
     umur
    -0.32
    ovec
    -0.31
    \}\\
    -0.31
    POSITIVE LOGITS
     resourceCulture
    0.79
    󠁴
    0.78
     Италијани
    0.76
    PyExc
    0.76
     Italijanski
    0.74
     Савезне
    0.71
    лтамалар
    0.69
    enderror
    0.67
     للاسماء
    0.66
     Administrativna
    0.64
    Act Density 0.004%

    No Known Activations