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

    Neuronpedia

    INDEX
    Explanations

    symbols and syntax structures commonly used in programming languages

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

    internal code and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.71
     ब्रेकडाउन
    -0.71
    rrggbb
    -0.69
    MessageTagHelper
    -0.68
    posedge
    -0.68
    FormTagHelper
    -0.68
     actionMode
    -0.66
    ItemBackground
    -0.66
    aarrggbb
    -0.65
    ंदीखरीदारी
    -0.65
    POSITIVE LOGITS
     internal
    0.84
    internal
    0.80
     Internal
    0.79
    Internal
    0.77
    INTERNAL
    0.73
     INTERNAL
    0.62
    内部
    0.61
     internally
    0.59
     interno
    0.54
     internals
    0.53
    Act Density 0.007%

    No Known Activations