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 never activates for any tokens, i.e. it appears to be inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Than
    -0.07
     bushes
    -0.06
     Piper
    -0.06
    .object
    -0.06
    Properties
    -0.06
     Harvard
    -0.06
    modifier
    -0.06
    nEnter
    -0.06
     erased
    -0.06
    _serializer
    -0.06
    POSITIVE LOGITS
     geniş
    0.07
    	ext
    0.06
    екар
    0.06
    _o
    0.06
    .qu
    0.06
     bursting
    0.05
    otel
    0.05
     přesně
    0.05
     рух
    0.05
    Tesla
    0.05
    Act Density 0.015%

    No Known Activations