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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash

    This neuron detects negation or contrast cues (e.g. words like “but,” “without,” “not”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    
    -0.06
    asa
    -0.06
    _bw
    -0.06
     Robotics
    -0.06
     touchdowns
    -0.06
     =&
    -0.06
    _LOW
    -0.06
    Logged
    -0.06
     dumped
    -0.06
     inflicted
    -0.06
    POSITIVE LOGITS
    surf
    0.07
    mysql
    0.06
     nevertheless
    0.06
     معد
    0.06
    클
    0.06
    _interest
    0.06
     Nevertheless
    0.06
    太阳城
    0.06
    attern
    0.06
    şk
    0.06
    Act Density 0.037%

    No Known Activations