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

    Neuronpedia

    INDEX
    Explanations

    specific institutional and scientific references in academic contexts

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

    Abbreviations and acronyms

    np_acts-logits-general · gemini-2.0-flash

    academic affiliations and publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     left
    -0.46
     Gouverneur
    -0.46
     Fieber
    -0.44
    APORE
    -0.43
     already
    -0.43
     unavoidable
    -0.43
    maining
    -0.42
     sportowe
    -0.42
     with
    -0.41
     pick
    -0.40
    POSITIVE LOGITS
    esModule
    0.68
     "..\..\..\
    0.63
     "..\..\
    0.62
     Мексичка
    0.61
    ConstraintMaker
    0.61
     UserDao
    0.59
     Meksiku
    0.59
    AxisAlignment
    0.57
    OCCURRED
    0.57
     pageContext
    0.56
    Act Density 0.561%

    No Known Activations