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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to scientific and mathematical concepts

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

    followed by "-ed", "-y", or "-al"

    np_acts-logits-general · gemini-2.0-flash

    temperature dependent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    juries
    -0.62
    ignment
    -0.61
    razos
    -0.61
    IDA
    -0.60
    iffs
    -0.60
    regard
    -0.60
    zmán
    -0.58
    伙
    -0.58
    ulante
    -0.58
    mindedness
    -0.58
    POSITIVE LOGITS
    Hentet
    0.82
     étrangères
    0.57
     abbastanza
    0.54
    存于互联网档案馆
    0.52
     culturelles
    0.52
     geworden
    0.51
    SharedDtor
    0.50
    LLocation
    0.50
     dependent
    0.50
    UnitTesting
    0.49
    Act Density 0.389%

    No Known Activations