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

    Neuronpedia

    INDEX
    Explanations

    Technology news articles

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to common function words (e.g. articles, conjunctions) and sentence-structuring punctuation (commas and periods).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _WARN
    -0.07
     barr
    -0.07
     rec
    -0.07
     арх
    -0.06
    107
    -0.06
     Shir
    -0.06
     nh
    -0.06
     Ferguson
    -0.06
    -0.06
     copies
    -0.06
    POSITIVE LOGITS
     Hemisphere
    0.06
     devlet
    0.06
     İnsan
    0.06
    �
    0.06
     }]
    0.06
    datum
    0.06
    opol
    0.06
    ugal
    0.06
     crippling
    0.06
    Future
    0.06
    Act Density 0.132%

    No Known Activations