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

    Neuronpedia

    INDEX
    Explanations

    occurrences of whitespace or spacing in the text

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

    Code, identifiers, and symbols

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resented
    -0.64
     kasarigan
    -0.62
     daddy
    -0.55
     apologised
    -0.55
    corresponding
    -0.54
     Dems
    -0.54
     melodrama
    -0.52
     sost
    -0.52
     amada
    -0.51
     inactivation
    -0.51
    POSITIVE LOGITS
    MethodManager
    0.62
    AnchorStyles
    0.61
    WriteAttribute
    0.57
     
    0.54
    SEGUIR
    0.54
     ?</
    0.51
    `,
    0.49
    .")
    0.49
    TagHelper
    0.49
    ♭
    0.49
    Act Density 0.273%

    No Known Activations