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

    Neuronpedia

    INDEX
    Explanations

    numbers or terms related to quantity and functionality in context

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

    all in one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.50
     avoit
    -0.48
     Riproduzione
    -0.45
     enfans
    -0.43
     zoude
    -0.41
     auroit
    -0.40
     égard
    -0.40
     rythme
    -0.40
     Sankt
    -0.40
    ScrollBar
    -0.39
    POSITIVE LOGITS
     AIO
    0.59
     versa
    0.50
     Combination
    0.48
    Combination
    0.48
     DIY
    0.45
     instant
    0.45
     Versatile
    0.44
     multifunctional
    0.44
     interlocking
    0.44
    DIY
    0.44
    Act Density 0.008%

    No Known Activations