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

    Neuronpedia

    INDEX
    Explanations

    different formats of identifiers or special characters in a technical context

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

    mathematical notation and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.75
    SequentialGroup
    -0.69
    ſſung
    -0.67
     témoig
    -0.67
     ſei
    -0.66
    ſicht
    -0.66
     好文分享
    -0.65
     NSCoder
    -0.65
    iſchen
    -0.65
     BoxDecoration
    -0.65
    POSITIVE LOGITS
    pak
    0.28
    üyada
    0.27
     etc
    0.26
    Poly
    0.26
    /}.
    0.25
    ↵
    0.24
    mstyle
    0.24
    <eos>
    0.24
    ัตว์
    0.24
     dran
    0.23
    Act Density 0.002%

    No Known Activations