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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to data collection and analysis

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

    meaning "all" or "everything."

    np_acts-logits-general · gemini-2.0-flash

    all data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     another
    -0.41
     sometimes
    -0.40
     ujednoznacz
    -0.40
    another
    -0.38
     précis
    -0.37
     something
    -0.37
     few
    -0.37
     certain
    -0.36
     perhaps
    -0.36
     parfois
    -0.36
    POSITIVE LOGITS
     Semua
    0.85
    的一切
    0.81
     everything
    0.79
    Everything
    0.77
     Everything
    0.77
    everything
    0.77
     모든
    0.76
     EVERYTHING
    0.75
    一切
    0.71
    Semua
    0.71
    Act Density 0.564%

    No Known Activations