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

    Neuronpedia

    INDEX
    Explanations

    Files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Král
    -0.06
     نق
    -0.06
     ру
    -0.06
     Tipo
    -0.06
     rut
    -0.06
    *num
    -0.06
    ной
    -0.06
     rethink
    -0.06
    GPU
    -0.06
     分
    -0.06
    POSITIVE LOGITS
    فهوم
    0.06
    using
    0.06
     TED
    0.06
    uddled
    0.06
    روج
    0.06
     pooled
    0.06
     odpově
    0.06
     hoá
    0.06
     caves
    0.06
    FK
    0.06
    Act Density 0.000%

    No Known Activations