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

    Neuronpedia

    INDEX
    Explanations

    sentences that express significant events or moments

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

    Sentences before enumeration

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     läßt
    -0.92
     muß
    -0.90
     idéia
    -0.77
     daß
    -0.77
     http
    -0.76
     !!!!!
    -0.76
     !!!
    -0.74
    !!!!!
    -0.72
     !!!!
    -0.72
    !!!!
    -0.71
    POSITIVE LOGITS
    Alongside
    0.97
     Alongside
    0.93
    “[
    0.91
    Luckily
    0.86
    Ultimately
    0.85
     enquanto
    0.85
     Notably
    0.84
     unsur
    0.84
     prioritizing
    0.83
     Ultimately
    0.83
    Act Density 0.142%

    No Known Activations