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

    Neuronpedia

    INDEX
    Explanations

    elements related to research, analysis, and comparatives within discussions

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

    language learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.86
     purpoſe
    -0.69
    ագրություններ
    -0.65
     myſelf
    -0.62
     pleaſure
    -0.61
     للمعارف
    -0.60
     Anſ
    -0.60
    opsida
    -0.59
    DockStyle
    -0.59
     ſind
    -0.59
    POSITIVE LOGITS
    expandindo
    0.32
     BytesLike
    0.28
     cooler
    0.28
     ebenso
    0.26
     обов
    0.25
    　　　　　　　　　　　　　　　　
    0.25
    arXiv
    0.25
    NSError
    0.25
    Dés
    0.25
     investissement
    0.25
    Act Density 0.366%

    No Known Activations