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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and formatting symbols

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

    End of turn markers

    np_acts-logits-general · gemini-2.0-flash

    programming markup and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.46
     Fer
    -0.45
    amoan
    -0.44
     verſ
    -0.44
     kapture
    -0.43
     ſch
    -0.43
    Fer
    -0.42
    Controllo
    -0.42
     ſind
    -0.42
    रीद
    -0.42
    POSITIVE LOGITS
    Geplaatst
    0.47
     kasarigan
    0.47
     MessageBoxIcon
    0.46
    TokenNameLPAREN
    0.45
     tartalomajánló
    0.45
    </thead>
    0.45
    EndContext
    0.43
    ísimo
    0.42
    StructEnd
    0.42
    devamını
    0.41
    Act Density 0.827%

    No Known Activations