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

    Neuronpedia

    INDEX
    Explanations

    claiming responsibility for attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Initialization
    -0.07
    摸
    -0.06
     chancellor
    -0.06
    بل
    -0.06
     Fehler
    -0.06
    但
    -0.06
     точки
    -0.06
     зда
    -0.05
    _blocked
    -0.05
    อส
    -0.05
    POSITIVE LOGITS
     ASD
    0.08
     eventually
    0.07
    ]bool
    0.07
    autos
    0.07
    stashop
    0.07
    šil
    0.06
    gh
    0.06
    ONUS
    0.06
     ThemeData
    0.06
    <>↵
    0.06
    Act Density 0.028%

    No Known Activations