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

    Neuronpedia

    INDEX
    Explanations

    ton

    np_max-act · gemini-2.0-flash

    The neuron activates on the names of the judges (e.g. the circuit judges listed in the opinion headers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LiveData
    -0.07
    .%
    -0.06
     ऊ
    -0.06
    ajar
    -0.06
     Saturn
    -0.06
     Sphere
    -0.06
    seconds
    -0.06
    datagrid
    -0.06
    iness
    -0.06
     alterations
    -0.06
    POSITIVE LOGITS
     пос
    0.07
    zie
    0.06
                            ↵
    0.06
    积
    0.06
     Στα
    0.06
    ("${
    0.06
    :numel
    0.06
    ISTER
    0.06
    ()][
    0.06
     quant
    0.06
    Act Density 0.014%

    No Known Activations