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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting in technical text

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

    shear rate $D/\dot{\gamma}$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwiſchen
    -1.45
     imagui
    -1.39
    ðsíða
    -1.38
     Geiſt
    -1.37
    ロウィン
    -1.37
    ésultats
    -1.37
    ſicht
    -1.37
    iſchen
    -1.36
     queſta
    -1.36
     zuſammen
    -1.35
    POSITIVE LOGITS
     and
    0.57
     The
    0.51
    ↵↵
    0.51
     (
    0.50
    ↵
    0.50
    -
    0.48
     
    0.48
      
    0.45
    _
    0.43
     &
    0.41
    Act Density 0.552%

    No Known Activations