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

    Neuronpedia

    INDEX
    Explanations

    Bridges

    np_max-act · gemini-2.0-flash

    The neuron fires on technical structural-engineering terms and measurements—especially words describing bridges (e.g. suspension, span, structure) and related construction vocabulary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     invisible
    -0.06
    _pan
    -0.06
     тка
    -0.06
    patch
    -0.06
    剩
    -0.06
     Ko
    -0.06
    ORTH
    -0.06
    ｯ
    -0.06
     yapılır
    -0.06
     以
    -0.06
    POSITIVE LOGITS
    Nie
    0.07
    $num
    0.06
     �
    0.06
    /↵
    0.06
     Nie
    0.06
     Specs
    0.06
    .community
    0.06
     novelty
    0.06
    	cv
    0.06
     starters
    0.06
    Act Density 0.016%

    No Known Activations