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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paste
    -0.08
     reviewers
    -0.07
     usage
    -0.07
    _reference
    -0.06
    気が
    -0.06
    ่ง
    -0.06
     slow
    -0.06
    存
    -0.06
     색
    -0.06
    ้
    -0.06
    POSITIVE LOGITS
     Throughout
    0.07
     Commissioners
    0.07
    .samples
    0.07
    -like
    0.07
    ModelState
    0.06
     recount
    0.06
    Cursor
    0.06
     Üniversitesi
    0.06
    Guild
    0.06
     VIDEO
    0.06
    Act Density 0.004%

    No Known Activations