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

    Neuronpedia

    INDEX
    Explanations

    references to language and its meanings

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

    meaning and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.66
    出版年
    -0.56
     invokingState
    -0.50
    __(/*!
    -0.50
     AssemblyCompany
    -0.48
    koľ
    -0.48
     AssemblyProduct
    -0.47
     autorytatywna
    -0.47
     AssemblyTitle
    -0.47
    SequentialGroup
    -0.46
    POSITIVE LOGITS
    ніципа
    0.39
    ApiRequest
    0.38
    High
    0.37
    lacht
    0.35
     يتيمه
    0.35
    SharedCtor
    0.35
    Grab
    0.35
    bulaire
    0.34
    Negative
    0.34
     bruja
    0.34
    Act Density 0.006%

    No Known Activations