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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (numbers and decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     법
    -0.06
    、私
    -0.06
    getEmail
    -0.06
    研究
    -0.05
     분류
    -0.05
    \Security
    -0.05
     método
    -0.05
     eines
    -0.05
     Hugh
    -0.05
    .section
    -0.05
    POSITIVE LOGITS
     bağ
    0.08
    лена
    0.07
    _refer
    0.07
     ByteArrayOutputStream
    0.06
     Sign
    0.06
    }

↵
    0.06
    概
    0.06
    بود
    0.06
     державного
    0.06
     composite
    0.06
    Act Density 0.105%

    No Known Activations