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

    Neuronpedia

    INDEX
    Explanations

    elements of generic data structure definitions and their instantiations

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

    graph reversal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrNil
    -0.57
     estekak
    -0.54
     ***!
    -0.54
    ᅠ
    -0.54
    JspWriter
    -0.53
     <>",
    -0.52
    IMPORTED
    -0.52
    -0.52
    点此举报
    -0.51
    astify
    -0.50
    POSITIVE LOGITS
     Exteriores
    0.44
    hermosa
    0.40
     parvenir
    0.40
     procéder
    0.39
    いかがでしょうか
    0.38
     asiatique
    0.38
     Wilayah
    0.38
     basically
    0.37
     oeufs
    0.36
     simplesmente
    0.36
    Act Density 0.011%

    No Known Activations