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

    Neuronpedia

    INDEX
    Explanations

    HTML or XML attributes and their values

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

    radio, decoration, src

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.60
     myſelf
    -0.59
     gynhyrchwyd
    -0.58
    iſen
    -0.57
    ementara
    -0.57
     semelh
    -0.56
     adesivos
    -0.56
     consommate
    -0.56
     ſch
    -0.54
     ſta
    -0.54
    POSITIVE LOGITS
    jspb
    0.43
    UnusedPrivate
    0.37
    localctx
    0.33
     nakalista
    0.32
    BitConverter
    0.31
     câu
    0.30
    GeneratedMessage
    0.30
     ó
    0.29
    цездатний
    0.29
     же
    0.28
    Act Density 0.041%

    No Known Activations