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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements, particularly colons and semicolons

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

    Follows a colon

    np_acts-logits-general · gemini-2.0-flash

    legal and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.85
    mybatisplus
    -0.80
    AndEndTag
    -0.77
    ValueStyle
    -0.77
     насељу
    -0.74
    OGND
    -0.73
    THISDAY
    -0.70
    ⓧ
    -0.68
    stdc
    -0.68
     ModelExpression
    -0.66
    POSITIVE LOGITS
     The
    1.12
    ↵↵
    1.10
     namely
    1.01
     “
    0.99
     the
    0.99
     It
    0.95
     There
    0.92
     They
    0.90
    namely
    0.89
     a
    0.89
    Act Density 0.246%

    No Known Activations