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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters commonly used in code syntax

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

    function call with side effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ruhe
    -0.40
     Begle
    -0.40
     Stamm
    -0.40
     informally
    -0.39
    y
    -0.39
     afloat
    -0.38
     exact
    -0.35
    _
    -0.35
     [
    -0.35
     embaraz
    -0.35
    POSITIVE LOGITS
    GEBURTSDATUM
    1.00
     незавершена
    0.78
    OGND
    0.77
    تقاوى
    0.77
    Хьажоргаш
    0.75
     BoxFit
    0.75
     Italijanski
    0.73
     pinulongan
    0.71
    хьтан
    0.70
    AndEndTag
    0.69
    Act Density 0.001%

    No Known Activations