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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Full
    -0.07
    elier
    -0.06
     GetMessage
    -0.06
    Jul
    -0.06
     Pick
    -0.06
    .Box
    -0.06
    SelectedItem
    -0.06
     paging
    -0.06
     Full
    -0.06
     活
    -0.06
    POSITIVE LOGITS
    vatel
    0.07
     friction
    0.07
    XR
    0.07
    ARENT
    0.07
    اورپ
    0.06
     دولتی
    0.06
    jaw
    0.06
     дорож
    0.06
    ManagerInterface
    0.06
    фици
    0.06
    Act Density 0.001%

    No Known Activations