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

    Neuronpedia

    INDEX
    Explanations

    words and symbols from source code, particularly Java

    oai_token-act-pair · gemini-2.0-flash

    Long data type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessFile
    -0.63
     Мексичка
    -0.63
     चीज़ों
    -0.58
     Dort
    -0.57
    :"-"`
    -0.57
    <bos>
    -0.56
    VIAF
    -0.55
     illet
    -0.55
    Autoritní
    -0.54
     spiro
    -0.54
    POSITIVE LOGITS
    Autowired
    0.46
    --)
    0.45
     mainly
    0.45
    tumblr
    0.45
    inflate
    0.44
    TestingModule
    0.44
    Salta
    0.43
    AnchorStyles
    0.43
    imer
    0.42
    AndroidJUnit
    0.42
    Act Density 5.176%

    No Known Activations