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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Key
    -0.08
    🅚
    -0.07
    챘
    -0.07
     Voters
    -0.07
     شيئ
    -0.07
     man
    -0.07
     dispar
    -0.07
     tkinter
    -0.07
    拙
    -0.06
    CursorPosition
    -0.06
    POSITIVE LOGITS
    (scene
    0.08
     settling
    0.08
     =>
    0.07
    альных
    0.07
    拜
    0.07
    늚
    0.07
    (done
    0.07
    改善
    0.06
    氦
    0.06
    (expr
    0.06
    Act Density 0.022%

    No Known Activations