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

    Neuronpedia

    INDEX
    Explanations

    the frequency of the word "several" and its related numerical values

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

    Quantities or numbers

    np_acts-logits-general · gemini-2.0-flash

    several followed by quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ////////////////
    -0.58
     Miki
    -0.58
    gridx
    -0.57
    –
    -0.55
    MessageTagHelper
    -0.55
     BoxDecoration
    -0.52
    WindowEvent
    -0.51
     TextStyle
    -0.51
     salva
    -0.51
    oucí
    -0.51
    POSITIVE LOGITS
     hundred
    1.31
     thousand
    1.19
     dozen
    1.15
    hundred
    1.01
     dizaines
    1.00
    dozen
    0.94
    thousand
    0.90
     centaines
    0.89
    Hundred
    0.89
     '{@
    0.87
    Act Density 0.271%

    No Known Activations