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

    Neuronpedia

    INDEX
    Explanations

    occurrences of opening and closing curly braces in the context of code or structured data formatting

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

    release year or publication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.57
     purpoſe
    -0.54
    Хьажоргаш
    -0.52
     queſta
    -0.52
     uſed
    -0.50
    цездатний
    -0.49
     utafitiHapana
    -0.47
     ſte
    -0.47
     raiſ
    -0.47
     tranſ
    -0.46
    POSITIVE LOGITS
    出版年
    0.45
    AutoScaleMode
    0.45
    textTheme
    0.43
     nahilalakip
    0.43
    insatz
    0.43
    Publicado
    0.42
    DockStyle
    0.41
    writerow
    0.41
     reinforces
    0.40
    ContentLoaded
    0.40
    Act Density 0.026%

    No Known Activations