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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash

    The neuron identifies references to case docket or file numbers (e.g. “No. 80-590”, “No. A-89-CA-1102”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SERVER
    -0.07
    .TEST
    -0.07
    jiště
    -0.07
    革
    -0.06
    hay
    -0.06
     Fransız
    -0.06
     Ops
    -0.06
    /train
    -0.06
    (nullable
    -0.06
     Prosper
    -0.06
    POSITIVE LOGITS
     eh
    0.07
    事情
    0.06
    ลาย
    0.06
    ิเศษ
    0.06
     где
    0.06
    .getSelectedItem
    0.06
     aren
    0.06
    นะ
    0.06
    997
    0.05
     demol
    0.05
    Act Density 0.001%

    No Known Activations