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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giants
    -0.07
     Disclosure
    -0.07
     เพ
    -0.07
    exp
    -0.07
     πρέπει
    -0.06
     زی
    -0.06
    573
    -0.06
    廳
    -0.06
     vos
    -0.06
     ورز
    -0.06
    POSITIVE LOGITS
     constructed
    0.10
     construction
    0.09
     Builder
    0.07
     building
    0.07
     built
    0.07
    ẹp
    0.07
    wind
    0.07
     snug
    0.06
    asto
    0.06
     builds
    0.06
    Act Density 0.036%

    No Known Activations