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

    Neuronpedia

    INDEX
    Explanations

    providing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hat
    -0.07
    -0.06
    Request
    -0.06
    unittest
    -0.06
     ilişk
    -0.06
    ']=='
    -0.06
     oranges
    -0.06
    OCI
    -0.06
     Buddha
    -0.06
     Reich
    -0.06
    POSITIVE LOGITS
     tolerated
    0.06
     Φ
    0.06
    aneous
    0.06
     khiển
    0.06
     OBJ
    0.06
     listings
    0.06
    	entry
    0.06
     translated
    0.06
     Danish
    0.06
     hefty
    0.06
    Act Density 0.023%

    No Known Activations