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

    Neuronpedia

    INDEX
    Explanations

    intensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     #(
    -0.06
     ',
    -0.06
    ozo
    -0.06
     azal
    -0.06
    сп
    -0.06
    nga
    -0.06
     oro
    -0.06
    retrieve
    -0.06
    benchmark
    -0.06
    茂
    -0.06
    POSITIVE LOGITS
     любой
    0.07
    歡
    0.07
     XCTest
    0.06
     exquisite
    0.06
     CHRIST
    0.06
     Mock
    0.06
     Covent
    0.06
     cruising
    0.06
     payloads
    0.06
    _Control
    0.06
    Act Density 0.000%

    No Known Activations