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

    Neuronpedia

    INDEX
    Explanations

    various forms of end punctuation and function delimiters typical in programming syntax

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

    Code snippets and file paths

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.58
    -
    -0.57
    ina
    -0.57
     law
    -0.54
    Eres
    -0.54
     power
    -0.52
     Kre
    -0.51
     mo
    -0.50
     e
    -0.50
    entet
    -0.50
    POSITIVE LOGITS
    Personensuche
    1.18
     <=",
    0.80
    ↵
    0.80
    __":
    0.72
    //.
    0.72
    sizeCache
    0.72
    __':
    0.67
     //
    0.67
    __":
    0.65
    ánicas
    0.62
    Act Density 0.304%

    No Known Activations