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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making, aiding, and providing support or enhancements

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

    followed by instructions or purposes

    np_acts-logits-general · gemini-2.0-flash

    to explain a purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saites
    -0.64
    bootstrapcdn
    -0.57
    Pautan
    -0.56
     GenerationType
    -0.56
     Domes
    -0.54
    ⓧ
    -0.54
    Географи
    -0.54
     firebaseConfig
    -0.53
     Jacobi
    -0.52
     JpaRepository
    -0.52
    POSITIVE LOGITS
    enumi
    0.83
     ול
    0.74
     better
    0.69
    انجليز
    0.69
    脚注の使い方
    0.65
    __":
    0.63
     بهتر
    0.62
     meglio
    0.60
    prnewswire
    0.59
     ולה
    0.58
    Act Density 0.492%

    No Known Activations