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

    Neuronpedia

    INDEX
    Explanations

    assignments or initializations of variables

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

    Equals sign

    np_acts-logits-general · gemini-2.0-flash

    assignment or comparison operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    -0.60
     Ș
    -0.58
    ly
    -0.58
    ’
    -0.57
    ness
    -0.56
    an
    -0.56
    ous
    -0.55
    o
    -0.54
    ess
    -0.53
    -
    -0.52
    POSITIVE LOGITS
    /=
    1.64
     CreateTagHelper
    1.50
     =
    1.32
    >=</
    1.25
    _=
    1.23
    }}=$
    1.23
    )]=
    1.20
     }}=
    1.16
    ))=
    1.15
    ))=\
    1.14
    Act Density 0.275%

    No Known Activations