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

    Neuronpedia

    INDEX
    Explanations

    high numerical values related to data points or measurements

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

    numbers containing 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.56
    +#+
    -0.47
     Mexique
    -0.46
    WriteTagHelper
    -0.43
     linkovi
    -0.42
     zune
    -0.42
     griech
    -0.41
     Ruang
    -0.40
     betweenstory
    -0.40
     griechischen
    -0.40
    POSITIVE LOGITS
    Revenir
    0.47
    jandro
    0.46
     Foundations
    0.44
    发表于
    0.44
     Lamont
    0.44
    afar
    0.43
     Yards
    0.43
     Jeremiah
    0.43
    eradish
    0.42
     injustice
    0.41
    Act Density 0.068%

    No Known Activations