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

    Neuronpedia

    INDEX
    Explanations

    statements related to claims, positions, or arguments in various contexts

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

    questions, reports, findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mention
    -0.36
     parmi
    -0.35
     among
    -0.34
    ariConfig
    -0.34
    琥
    -0.33
    ))(
    -0.33
     sable
    -0.33
     diamant
    -0.33
     AMONG
    -0.32
    aronder
    -0.32
    POSITIVE LOGITS
    WebElementEntity
    0.55
    WaitGroup
    0.54
    MessageOf
    0.54
    addCriterion
    0.53
     EconPapers
    0.53
    0.52
     NavController
    0.51
     surla
    0.50
    mybatisplus
    0.49
    انجليز
    0.48
    Act Density 0.071%

    No Known Activations