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

    Neuronpedia

    INDEX
    Explanations

    Piping

    np_max-act · gemini-2.0-flash

    This neuron detects technical terms for physical connection channels—pipes, lines, conduits, etc., in engineering descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _WR
    -0.07
     Forced
    -0.06
    /company
    -0.06
    _signup
    -0.06
     عبارت
    -0.06
    has
    -0.06
     mosque
    -0.06
     Starbucks
    -0.06
    Console
    -0.06
    청
    -0.06
    POSITIVE LOGITS
    “My
    0.07
     ihrem
    0.06
     случаев
    0.06
    .friend
    0.06
     Pants
    0.06
    DMIN
    0.06
    ETIME
    0.06
     cuenta
    0.06
    移動
    0.06
    (Column
    0.06
    Act Density 0.039%

    No Known Activations