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
     cellFor
    -0.07
    @a
    -0.07
     реє
    -0.06
    antanamo
    -0.06
     zaten
    -0.06
     chết
    -0.06
    DIR
    -0.06
    _MISSING
    -0.06
    CppType
    -0.06
    _logging
    -0.06
    POSITIVE LOGITS
     pute
    0.07
    "/>
    0.06
    _attr
    0.06
     aggregation
    0.06
    illard
    0.06
     Horizon
    0.06
    }))
    0.06
     dễ
    0.06
    aber
    0.06
     делать
    0.06
    Act Density 0.000%

    No Known Activations