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

    Neuronpedia

    INDEX
    Explanations

    relation.binary.propositionalequality.refl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urangi
    0.44
    phill
    0.39
    CID
    0.39
    KINS
    0.38
    ભાઇ
    0.37
    Notification
    0.37
    Idle
    0.37
    times
    0.37
    backend
    0.37
     എന്നാല്‍
    0.37
    POSITIVE LOGITS
     पीड़
    0.39
    ём
    0.39
     használ
    0.39
    ică
    0.39
     dataGenerator
    0.39
     Zahlen
    0.39
    ໍາ
    0.38
     stockholders
    0.38
     creme
    0.38
     أص
    0.38
    Act Density 0.002%

    No Known Activations