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

    Neuronpedia

    INDEX
    Explanations

    REE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diam
    -0.07
    的な
    -0.07
     waar
    -0.07
    灣
    -0.06
    UpEdit
    -0.06
     Peters
    -0.06
     Kashmir
    -0.06
     Athen
    -0.06
     Fried
    -0.06
    Cmd
    -0.06
    POSITIVE LOGITS
    vasion
    0.06
    (xml
    0.06
    (dialog
    0.06
    rray
    0.06
    High
    0.06
     громадян
    0.06
    Meanwhile
    0.06
    _Index
    0.06
    Messenger
    0.06
    ॰
    0.06
    Act Density 0.000%

    No Known Activations