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

    Neuronpedia

    INDEX
    Explanations

    sentences conveying a sense of urgency about health or risk

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

    Followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.69
     برانيه
    -0.60
    Diweddarwch
    -0.59
     referrerpolicy
    -0.59
     ConstraintSet
    -0.59
     snippetHide
    -0.58
    TemporalType
    -0.57
     ویکی‌آمباردا
    -0.57
     الحره
    -0.57
    ագրություններ
    -0.57
    POSITIVE LOGITS
    kregen
    0.36
    galkan
    0.35
    väg
    0.33
     útiles
    0.33
     isolada
    0.32
     duele
    0.32
     conocemos
    0.31
     sientes
    0.31
     aisladas
    0.31
     segala
    0.30
    Act Density 9.553%

    No Known Activations