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

    Neuronpedia

    INDEX
    Explanations

    code blocks and syntax in programming languages, particularly related to class and function definitions

    oai_token-act-pair · gemini-2.0-flash

    foreign language words

    np_token-act-pair-logits · gpt-4o-mini

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.84
    Portály
    -0.80
     autorytatywna
    -0.76
    TestingModule
    -0.76
     <=",
    -0.72
    fortawesome
    -0.71
    HandlerContext
    -0.69
    !*\
    -0.68
    rinfo
    -0.64
    writeField
    -0.63
    POSITIVE LOGITS
     disponibilités
    0.47
    Porter
    0.45
     väx
    0.44
     econô
    0.44
    ğ
    0.44
     henkil
    0.44
    Geplaatst
    0.44
    vänt
    0.43
     Porter
    0.43
    売り
    0.43
    Act Density 0.421%

    No Known Activations