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

    Neuronpedia

    INDEX
    Explanations

    multiple languages detected

    np_max-act · gemini-2.0-flash

    The neuron detects romanized Chinese syllables (Pinyin or Cantonese Jyutping) that include a tone number at the end.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cue
    -0.06
    .Completed
    -0.06
     Rounds
    -0.06
    ])
↵
    -0.06
     pre
    -0.06
     MIT
    -0.06
    /fa
    -0.06
     continuous
    -0.06
     LC
    -0.06
    _KeyDown
    -0.06
    POSITIVE LOGITS
    .isBlank
    0.07
     coming
    0.07
     τι
    0.07
    optional
    0.06
    คอม
    0.06
     Exercises
    0.06
     peel
    0.06
    ]+
    0.06
    	point
    0.06
     void
    0.06
    Act Density 0.018%

    No Known Activations