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

    Neuronpedia

    INDEX
    Explanations

    references to data analysis techniques or algorithms

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

    Numbers within tables or charts

    np_acts-logits-general · gemini-2.0-flash

    languages and cultural terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    -0.62
     some
    -0.53
     (
    -0.52
    乓
    -0.48
    !
    -0.47
     where
    -0.47
     has
    -0.47
     a
    -0.47
     "
    -0.47
     by
    -0.46
    POSITIVE LOGITS
    TagMode
    0.88
     initComponents
    0.85
    awtextra
    0.83
    __":
    0.81
     CURIAM
    0.80
    __':
    0.79
     مرئيه
    0.79
    WriteTagHelper
    0.77
    AndEndTag
    0.76
    ConstraintMaker
    0.76
    Act Density 1.163%

    No Known Activations