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

    Neuronpedia

    INDEX
    Explanations

    words related to action or events

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

    "construction", "instructions", or "conduct"

    np_acts-logits-general · gemini-2.0-flash

    construction and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.87
    AsUp
    -0.77
    cornerRadius
    -0.76
    лерея
    -0.74
    iverr
    -0.73
     Kuz
    -0.72
     Maren
    -0.71
    cules
    -0.71
    rrggbb
    -0.71
     useCallback
    -0.71
    POSITIVE LOGITS
    🤣🤣
    0.75
     instructions
    0.69
    tır
    0.69
    sst
    0.68
     Hector
    0.65
    ی
    0.65
    iect
    0.63
     ASTR
    0.62
    Hector
    0.61
    0.60
    Act Density 0.173%

    No Known Activations