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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their roles or contributions

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

    Occurrences with numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.01
    .",
    -0.99
    `,
    -0.97
     utafitiHapana
    -0.96
    saraba
    -0.94
     nahilalakip
    -0.93
    تقاوى
    -0.92
     saites
    -0.89
    '],
    -0.86
    '},
    -0.86
    POSITIVE LOGITS
    ↵↵
    0.91
    ↵
    0.85
    ↵↵↵
    0.83
     +
    0.83
     &
    0.80
     /
    0.78
     |
    0.75
    /
    0.67
     //
    0.65
     =
    0.64
    Act Density 0.795%

    No Known Activations