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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence and expectations

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

    certainty and expectation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.29
    ’
    -0.29
     lecteur
    -0.29
     exposure
    -0.29
    JsonHelper
    -0.28
     finalmente
    -0.28
    有所
    -0.28
     suddenly
    -0.27
     supermarket
    -0.27
    ⅘
    -0.27
    POSITIVE LOGITS
     ProtoMessage
    0.73
    webElementXpaths
    0.68
    HasForeignKey
    0.65
    fjspx
    0.63
    出版年
    0.63
     Италијани
    0.59
    haikusbot
    0.59
     ErrIntOverflow
    0.59
     oprot
    0.58
    exels
    0.56
    Act Density 0.036%

    No Known Activations