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

    Neuronpedia

    INDEX
    Explanations

    the word "below" in various contexts

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

    "below"

    np_acts-logits-general · gemini-2.0-flash

    introducing content below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.94
     nahilalakip
    -0.91
     تضيفلها
    -0.89
     MainAxisSize
    -0.85
     "..\..\
    -0.84
    dafx
    -0.83
    astéroïdes
    -0.83
    djangoproject
    -0.83
    sizeCache
    -0.82
    mergeFrom
    -0.82
    POSITIVE LOGITS
    Downs
    0.73
    downs
    0.71
     down
    0.70
     below
    0.66
     Downs
    0.66
    👇
    0.63
     DOWN
    0.59
     descent
    0.59
     downs
    0.59
     beneath
    0.57
    Act Density 0.275%

    No Known Activations