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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or references to multiple items or concepts

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

    Follows "many," "numerous," or "few."

    np_acts-logits-general · gemini-2.0-flash

    many, numerous, few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dovrebbero
    -0.54
    Slf
    -0.52
     organelles
    -0.50
     chirurgie
    -0.49
     arba
    -0.48
    のではなく
    -0.47
    某种
    -0.46
     ANYTHING
    -0.45
     eller
    -0.45
     hjælp
    -0.45
    POSITIVE LOGITS
     other
    0.76
    TagMode
    0.72
     betweenstory
    0.71
     different
    0.69
    المناصب
    0.68
    <tfoot>
    0.68
     ऐसे
    0.68
    ,:),
    0.66
    archiviato
    0.65
    InitVars
    0.64
    Act Density 0.401%

    No Known Activations