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

    Neuronpedia

    INDEX
    Explanations

    mathematical structures and notation related to equations

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

    Mathematical or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    Davis Gilbert Bick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Knot
    -0.74
     cognac
    -0.71
     Cognac
    -0.70
     locust
    -0.69
     Monarch
    -0.68
     Borough
    -0.68
    borough
    -0.67
     garlic
    -0.66
     Butterworth
    -0.66
     Cough
    -0.65
    POSITIVE LOGITS
     Davis
    0.73
     Bick
    0.72
    Davis
    0.68
     Wint
    0.63
     Gilbert
    0.63
     CD
    0.61
     Nis
    0.59
     Watt
    0.58
     RDC
    0.57
    Gilbert
    0.57
    Act Density 1.141%

    No Known Activations