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

    Neuronpedia

    INDEX
    Explanations

    phrases related to passwords and access management

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

    Numbers or quantities

    np_acts-logits-general · gemini-2.0-flash

    numbers following quantity words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.75
    setVerticalGroup
    -0.71
     незавершена
    -0.65
     Савезне
    -0.65
     Autorisations
    -0.62
     autorytatywna
    -0.59
     desmotivaciones
    -0.57
     increí
    -0.56
    adaptiveStyles
    -0.56
     パンチラ
    -0.54
    POSITIVE LOGITS
     appunto
    0.47
     столько
    0.44
     twelve
    0.41
     thirteen
    0.40
     twenty
    0.37
     ten
    0.36
     tyle
    0.36
    これだけ
    0.35
    整整
    0.35
    这么多
    0.34
    Act Density 1.152%

    No Known Activations