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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations related to unitary operators and matrices in linear algebra

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

    mathematical notation subscripts and superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.48
     slide
    -0.47
     slick
    -0.47
    omalainen
    -0.44
     fellows
    -0.42
     co
    -0.42
     commercial
    -0.41
     scholar
    -0.41
     civic
    -0.41
     short
    -0.41
    POSITIVE LOGITS
    AutoScaleMode
    0.66
     OFDb
    0.64
     MainAxisSize
    0.55
     setTotal
    0.54
     tartalomajánló
    0.53
     ſche
    0.50
     ſtand
    0.50
     ModelRenderer
    0.49
    ſelf
    0.48
     GetAll
    0.47
    Act Density 0.869%

    No Known Activations