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

    Neuronpedia

    INDEX
    Explanations

    sections indicating document structure or formatting details

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

    Citations or references

    np_acts-logits-general · gemini-2.0-flash

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.45
     >=",
    -0.44
     nahilalakip
    -0.41
    Selfer
    -0.40
    theless
    -0.38
     noDo
    -0.38
     OFDb
    -0.37
    tomans
    -0.37
     CommonModule
    -0.36
     consigo
    -0.36
    POSITIVE LOGITS
     препратки
    0.65
    Autoritní
    0.51
     Gute
    0.46
    ală
    0.44
     hend
    0.43
    Spoljašnje
    0.42
    jęt
    0.42
     Мексичка
    0.41
     gând
    0.41
    0.41
    Act Density 0.363%

    No Known Activations