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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hal
    -0.06
     fridge
    -0.06
     building
    -0.06
     healthy
    -0.06
    ("↵
    -0.06
     Microsystems
    -0.06
    َت
    -0.06
    IRROR
    -0.06
    ека
    -0.06
     Engines
    -0.06
    POSITIVE LOGITS
    ￣￣￣
    0.07
    _instances
    0.07
     wav
    0.06
     тов
    0.06
     euros
    0.06
    _wifi
    0.06
    COORD
    0.06
    Wie
    0.06
     Princip
    0.06
     genres
    0.06
    Act Density 0.005%

    No Known Activations