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

    Neuronpedia

    INDEX
    Explanations

    numerical values or data representations related to scientific research

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

    Follows periods in URLs or references

    np_acts-logits-general · gemini-2.0-flash

    numbers within parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.10
    ChildScrollView
    -1.06
    sidemargin
    -1.01
    rrggbb
    -1.01
    abestanden
    -1.00
    GEBURTSDATUM
    -0.99
     themſelves
    -0.96
     itſelf
    -0.96
     الحره
    -0.96
     Roskov
    -0.95
    POSITIVE LOGITS
     "
    0.58
     “
    0.54
     '
    0.54
    ...
    0.53
     so
    0.52
     for
    0.52
     is
    0.51
     a
    0.51
    <eos>
    0.49
     (
    0.49
    Act Density 0.371%

    No Known Activations