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

    Neuronpedia

    INDEX
    Explanations

    External

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    によ
    -0.07
    in
    -0.06
    achines
    -0.06
     plausible
    -0.06
     shade
    -0.06
     prayer
    -0.06
     Province
    -0.06
     Section
    -0.06
     OCR
    -0.06
     shrink
    -0.06
    POSITIVE LOGITS
     обязан
    0.07
    ี.
    0.07
    роч
    0.07
    @property
    0.06
     лич
    0.06
    /plain
    0.06
     BASIS
    0.06
    StoryboardSegue
    0.06
     Bachelor
    0.06
    兰
    0.06
    Act Density 0.003%

    No Known Activations