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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements, specifically focusing on closing brackets and commas

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

    code structure and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Coordenadas
    -0.38
     Gon
    -0.35
     zij
    -0.35
    ține
    -0.35
     Zen
    -0.35
    ఠ
    -0.35
    应当
    -0.34
     BoxDecoration
    -0.34
    drake
    -0.34
     Core
    -0.34
    POSITIVE LOGITS
    Personendaten
    0.93
    GEBURTSDATUM
    0.78
    endphp
    0.66
    ThroughAttribute
    0.64
     OMITBAD
    0.62
    Хьажоргаш
    0.54
    +#+#
    0.53
     betweenstory
    0.53
     հղումներ
    0.51
    addCriterion
    0.49
    Act Density 0.003%

    No Known Activations