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

    Neuronpedia

    INDEX
    Explanations

    specific references to technical specifications and functionalities within documentations or reports

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

    application and case contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лтемелер
    -0.62
     pleaſure
    -0.61
     arşivlendi
    -0.53
    ContentLoaded
    -0.52
    ंदीखरीदारी
    -0.51
    ніципа
    -0.45
     burbujas
    -0.44
    Chham
    -0.44
     Houſe
    -0.44
     Taktlose
    -0.43
    POSITIVE LOGITS
     existing
    0.41
     mergeFrom
    0.36
    kasse
    0.33
    saraba
    0.33
    XmlAccessorType
    0.32
    bolt
    0.32
    dahl
    0.32
     reform
    0.32
     dumps
    0.31
     colic
    0.31
    Act Density 0.106%

    No Known Activations