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

    Neuronpedia

    INDEX
    Explanations

    making a request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vila
    0.38
    Gather
    0.37
    ALITY
    0.37
     명령어
    0.36
    గ్ర
    0.34
     polarity
    0.34
     نشر
    0.34
    0.34
    τιο
    0.33
     invariants
    0.33
    POSITIVE LOGITS
     request
    2.25
    请求
    2.11
     requesting
    2.06
    request
    2.05
     Request
    2.05
     requests
    1.97
     درخواست
    1.96
     REQUEST
    1.96
    Request
    1.94
     요청
    1.92
    Act Density 0.019%

    No Known Activations