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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naveg
    -0.07
     PASSWORD
    -0.07
     Cone
    -0.07
    حدة
    -0.06
    ियन
    -0.06
    Level
    -0.06
    Launcher
    -0.06
    MENU
    -0.06
     Diploma
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     at
    0.08
     updater
    0.07
    파
    0.07
    -paid
    0.06
     EVT
    0.06
     Katy
    0.06
    ancy
    0.06
    аты
    0.06
    /by
    0.06
    열
    0.06
    Act Density 0.024%

    No Known Activations