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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating possession or relation

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

    after of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behaviors
    -0.38
    Erreferentziak
    -0.36
    nesses
    -0.36
    oarece
    -0.34
     Behaviors
    -0.34
     Perfon
    -0.33
     Afin
    -0.33
    simum
    -0.33
    yecek
    -0.32
    haviors
    -0.32
    POSITIVE LOGITS
     '\\;'
    0.58
     CreateTagHelper
    0.54
    دانشنامهٔ
    0.53
    simpleType
    0.52
     незавершена
    0.50
    帖最后由
    0.48
    ragalactic
    0.48
    enumi
    0.47
     переписи
    0.47
    __(/*!
    0.47
    Act Density 0.154%

    No Known Activations