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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash

    This neuron detects standalone numeric measurements, especially floating-point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    उन
    -0.07
     वर
    -0.07
     于
    -0.06
    ref
    -0.06
     nem
    -0.06
    _im
    -0.06
     STA
    -0.06
    ประก
    -0.06
    Daniel
    -0.06
    PDF
    -0.06
    POSITIVE LOGITS
    .Team
    0.06
    Vectorizer
    0.06
     суд
    0.06
     точ
    0.06
    	request
    0.06
    949
    0.06
     amnesty
    0.06
     Pars
    0.06
     mounting
    0.06
     kimse
    0.06
    Act Density 0.010%

    No Known Activations