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

    Neuronpedia

    INDEX
    Explanations

    Population and production

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DI
    -0.08
    전
    -0.07
     artery
    -0.07
     can
    -0.07
    PDF
    -0.07
     opened
    -0.07
     duke
    -0.07
    (Input
    -0.07
     mắt
    -0.06
     disabled
    -0.06
    POSITIVE LOGITS
     réalis
    0.08
    (layers
    0.07
    ерб
    0.06
    _markers
    0.06
    вок
    0.06
     совершенно
    0.06
     зрост
    0.06
     endors
    0.06
     �
    0.06
     解
    0.06
    Act Density 0.050%

    No Known Activations