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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash

    This neuron detects the start of parenthetical asides (opening parentheses).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     networks
    -0.08
     receptor
    -0.07
     bail
    -0.07
     acquire
    -0.07
     bombers
    -0.07
     Croatia
    -0.07
    forall
    -0.06
     makers
    -0.06
     attorney
    -0.06
     propagation
    -0.06
    POSITIVE LOGITS
     způsobem
    0.07
    [V
    0.06
     autobi
    0.06
     způsob
    0.06
    [..
    0.06
    iores
    0.06
    เภ
    0.06
     �
    0.06
    .ensure
    0.06
    !")↵↵
    0.06
    Act Density 0.004%

    No Known Activations