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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "many."

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

    "Many" followed by expressions of gratitude or quantity

    np_acts-logits-general · gemini-2.0-flash

    many followed by counts or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.51
     κάθε
    -0.50
    <i>
    -0.48
    -0.48
    filepath
    -0.48
    lin
    -0.48
    SE
    -0.47
     somehow
    -0.47
    alom
    -0.47
    ="#"><
    -0.46
    POSITIVE LOGITS
     MANY
    1.11
    MANY
    1.05
     times
    0.89
     many
    0.84
     CreateTagHelper
    0.83
    MLLoader
    0.82
     tausend
    0.81
     Many
    0.81
    many
    0.80
     different
    0.79
    Act Density 0.123%

    No Known Activations