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

    Neuronpedia

    INDEX
    Explanations

    Python syntax elements related to module imports and main execution blocks

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

    Code or filepath references containing "__"

    np_acts-logits-general · gemini-2.0-flash

    __dir__ or aspirate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.59
     سكانية
    -0.56
    tonsoft
    -0.56
     createStore
    -0.53
    tagHelperRunner
    -0.48
    domada
    -0.48
     كومونز
    -0.48
    出版年
    -0.47
    nologies
    -0.46
    phalt
    -0.45
    POSITIVE LOGITS
     __
    0.88
    (__
    0.72
    Personendaten
    0.70
    __
    0.68
     "__
    0.64
    __.__
    0.63
    argv
    0.60
     '__
    0.59
    .__
    0.56
     script
    0.54
    Act Density 0.117%

    No Known Activations