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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or states of being

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

    reporting past actions or current states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.57
    <()>
    -0.56
    endphp
    -0.54
     estekak
    -0.53
     pageContext
    -0.52
    __":
    -0.52
    enment
    -0.48
     iconFacebook
    -0.47
    __":
    -0.47
    WireFormatLite
    -0.47
    POSITIVE LOGITS
    ViewImports
    0.53
    INCREF
    0.46
    jednoc
    0.40
     AssemblyCompany
    0.40
    FormBorderStyle
    0.38
    wüns
    0.37
     diversidad
    0.37
     različ
    0.36
     diversité
    0.35
    ണ
    0.34
    Act Density 0.061%

    No Known Activations