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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .vertices
    -0.07
     avoided
    -0.07
    YRO
    -0.06
     pare
    -0.06
     到
    -0.06
    /payment
    -0.06
    _SLEEP
    -0.06
     narrator
    -0.06
     wave
    -0.06
     adequately
    -0.06
    POSITIVE LOGITS
    okableCall
    0.07
    ��
    0.07
    @synthesize
    0.07
    گاه
    0.07
     fName
    0.06
    북도
    0.06
    Understanding
    0.06
    撃
    0.06
    tributes
    0.06
    	RTDBG
    0.06
    Act Density 0.010%

    No Known Activations