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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions of love and emotional connection

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

    "I" followed by auxiliary verbs or related words

    np_acts-logits-general · gemini-2.0-flash

    opinions and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ępnie
    -0.71
     Commencez
    -0.70
    URLException
    -0.64
    .*/
    -0.63
     затем
    -0.60
    wnież
    -0.59
    ніципалі
    -0.59
    .。
    -0.59
     réessayer
    -0.58
     позже
    -0.57
    POSITIVE LOGITS
     [
    0.52
    celana
    0.49
     بيها
    0.47
    getMenuInflater
    0.46
     absolutely
    0.46
    ագրություններ
    0.45
     版
    0.44
    Jîn
    0.44
    TypedDataSet
    0.43
     رائ
    0.43
    Act Density 0.217%

    No Known Activations