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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and structures related to topology and spaces

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

    Mathematical notation using LaTeX

    np_acts-logits-general · gemini-2.0-flash

    mathematical definitions and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.42
     bug
    -0.42
    ...
    -0.41
    .
    -0.41
    ↵↵↵
    -0.41
     Lake
    -0.40
     long
    -0.40
     i
    -0.39
     {
    -0.39
    <
    -0.38
    POSITIVE LOGITS
    tvguidetime
    0.93
    الحياه
    0.91
    setVerticalGroup
    0.88
    Personensuche
    0.86
     Paglinawan
    0.81
    expandindo
    0.80
    省市镇
    0.79
     ujednoznacz
    0.78
    WithIOException
    0.78
     HasFactory
    0.78
    Act Density 2.917%

    No Known Activations