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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or statistical data related to scientific studies

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

    Numbers that start a sentence

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NUMX
    -0.81
    — 
    -0.80
     становника
    -0.78
    FundMe
    -0.68
    〢
    -0.67
    chọn
    -0.64
     Ngb
    -0.62
     -->>
    -0.61
    ſhip
    -0.61
    ertale
    -0.60
    POSITIVE LOGITS
    <eos>
    0.86
    ↵↵
    0.77
    ↵↵↵↵
    0.71
    0
    0.69
    )
    0.66
    ↵
    0.65
    ↵↵↵
    0.65
    2
    0.65
    5
    0.64
    1
    0.64
    Act Density 0.951%

    No Known Activations