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

    Neuronpedia

    INDEX
    Explanations

    structured list items or references to citation notes

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

    Text enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.56
     a
    -0.54
     
    -0.53
    the
    -0.53
    The
    -0.52
    </em>
    -0.51
    ‘
    -0.51
    2
    -0.51
     For
    -0.51
    </i>
    -0.50
    POSITIVE LOGITS
     propOrder
    1.35
    __':
    1.31
    __":
    1.28
     تانيه
    1.17
    ReusableCell
    1.17
     متعلقه
    1.10
     المعيارى
    1.10
    AndEndTag
    1.09
    tagHelperRunner
    1.07
    rungsseite
    1.06
    Act Density 0.183%

    No Known Activations