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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations or expressions involving equality signs

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

    mathematical equality assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.61
     monica
    -0.54
    BufferException
    -0.53
    MLLoader
    -0.52
    RefNanny
    -0.50
    balleur
    -0.49
     Grüsse
    -0.49
    ukone
    -0.46
     Chriftian
    -0.45
     Saviour
    -0.45
    POSITIVE LOGITS
     &=
    1.76
    &=
    1.29
     &=&
    0.98
    &=\
    0.96
     ||=
    0.86
     $=
    0.85
    |=
    0.82
    $=
    0.82
    ))=
    0.79
    &=&
    0.76
    Act Density 0.025%

    No Known Activations