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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and symbols used in equations

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

    Symbols followed by the number 1

    np_acts-logits-general · gemini-2.0-flash

    sequences followed by 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forty
    -0.51
     thirty
    -0.50
    thirty
    -0.47
     seven
    -0.47
     eight
    -0.47
     fifty
    -0.46
     twenty
    -0.46
    forty
    -0.45
     seventy
    -0.44
    Forty
    -0.43
    POSITIVE LOGITS
     виправивши
    0.81
     estekak
    0.80
    .*")]
    0.80
     UNO
    0.76
     MaterialApp
    0.75
     one
    0.74
    unity
    0.74
     unity
    0.72
    ]")]
    0.71
     ONE
    0.71
    Act Density 0.894%

    No Known Activations