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

    Neuronpedia

    INDEX
    Explanations

    selector

    np_max-act · gemini-2.0-flash

    The neuron activates on CSS selector tokens and related syntax (e.g. “selector”, “>”, combinators).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    izr
    -0.07
    CONF
    -0.07
     जग
    -0.06
    �
    -0.06
    Containers
    -0.06
    ปร
    -0.06
     umbrella
    -0.06
    createdAt
    -0.06
     Cable
    -0.06
    地球
    -0.06
    POSITIVE LOGITS
    unting
    0.07
     "");
    0.06
     bos
    0.06
     lúc
    0.06
     destructive
    0.06
    iei
    0.06
    _trip
    0.06
     avantaj
    0.06
    oningen
    0.06
    ﾚ
    0.06
    Act Density 0.012%

    No Known Activations