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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions related to linear algebra or operations in vector spaces

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

    mathematical operators and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.38
     opra
    -0.35
     namanya
    -0.35
    stufe
    -0.34
     useEffect
    -0.34
     dosages
    -0.34
    uthorized
    -0.34
     directions
    -0.34
    Glej
    -0.34
     Grüßen
    -0.34
    POSITIVE LOGITS
     informée
    0.75
     estekak
    0.68
     BoxDecoration
    0.64
     betweenstory
    0.63
    AnimationsModule
    0.62
     OMITBAD
    0.60
     autorytatywna
    0.59
    rB
    0.52
     SQLAlchemy
    0.52
     endblock
    0.52
    Act Density 1.453%

    No Known Activations