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

    Neuronpedia

    INDEX
    Explanations

    references to visual formatting elements or annotations

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

    mixed domain text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.72
    GEBURTS
    -0.65
    XmlAccessorType
    -0.65
    __':
    -0.63
     queſta
    -0.60
    󠁮
    -0.59
     getattr
    -0.56
    fromnode
    -0.54
     $_(
    -0.54
     laſſen
    -0.54
    POSITIVE LOGITS
    Demikian
    0.43
     Company
    0.40
     кот
    0.38
     include
    0.37
    หนัก
    0.37
    arbeitung
    0.36
     renovables
    0.36
    ,
    0.35
     Buildings
    0.35
    principalTable
    0.35
    Act Density 0.144%

    No Known Activations