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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _behavior
    -0.08
     Sugar
    -0.06
     Ranch
    -0.06
    translated
    -0.06
    Context
    -0.06
     modest
    -0.06
     completion
    -0.06
     Mori
    -0.06
    جو
    -0.06
    ulario
    -0.06
    POSITIVE LOGITS
     نفت
    0.07
     leaderboard
    0.07
     TMPro
    0.07
     Athens
    0.07
    [l
    0.06
     dlg
    0.06
     userinfo
    0.06
     앉
    0.06
     اس
    0.06
     čá
    0.06
    Act Density 0.004%

    No Known Activations