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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions related to financial metrics and statistics

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

    before time units

    np_acts-logits-general · gemini-2.0-flash

    quantities and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avadoc
    -0.60
    Obec
    -0.54
    ThemeOverlay
    -0.53
    Anytime
    -0.52
     قلي
    -0.52
     youngest
    -0.52
     Oldest
    -0.51
    asmuch
    -0.51
     aceptas
    -0.51
    částí
    -0.51
    POSITIVE LOGITS
     hundreds
    1.75
     thousands
    1.69
    thousands
    1.54
     dozens
    1.51
    hundreds
    1.50
     millions
    1.49
     Hundreds
    1.49
    Thousands
    1.49
     Thousands
    1.45
     tens
    1.39
    Act Density 0.311%

    No Known Activations