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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /km
    -0.07
    оу
    -0.06
    	em
    -0.06
    tras
    -0.06
    _U
    -0.06
    strategy
    -0.06
    __()
    -0.06
     fin
    -0.06
    ('./
    -0.06
     decorator
    -0.06
    POSITIVE LOGITS
     přib
    0.07
     Quyết
    0.07
     приклад
    0.07
    }`}
    0.07
    }@
    0.07
     shirt
    0.07
    })
    0.07
     روی
    0.07
     hungry
    0.06
     基
    0.06
    Act Density 0.000%

    No Known Activations