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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or equations involving equality

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

    equivalence or congruence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.50
    ThroughAttribute
    -0.47
     Taft
    -0.43
     réal
    -0.43
     løpet
    -0.42
     descubrimiento
    -0.41
    Mathematics
    -0.41
     Making
    -0.40
    settlement
    -0.40
     Kartoffeln
    -0.40
    POSITIVE LOGITS
    equiv
    2.56
    ≡
    1.59
     equiv
    1.35
    triangleq
    0.77
    0.75
    quiv
    0.67
     congruent
    0.67
     unequiv
    0.67
     Equ
    0.65
     equivalent
    0.62
    Act Density 0.018%

    No Known Activations