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

    Neuronpedia

    INDEX
    Explanations

    189

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rockets
    -0.07
    roups
    -0.07
    (sequence
    -0.07
     situation
    -0.07
    Urls
    -0.07
    Navigation
    -0.07
    Jac
    -0.07
    计
    -0.07
    川
    -0.06
     ApplicationContext
    -0.06
    POSITIVE LOGITS
    189
    0.31
    188
    0.26
    187
    0.22
    186
    0.21
    185
    0.18
    190
    0.07
    єв
    0.07
    879
    0.07
    209
    0.07
    보
    0.07
    Act Density 0.015%

    No Known Activations