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

    Neuronpedia

    INDEX
    Explanations

    sitting down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stem
    -0.06
     pull
    -0.06
    ち
    -0.06
     INST
    -0.06
    THE
    -0.06
     Jaw
    -0.06
     OSError
    -0.06
     Нав
    -0.06
    Senator
    -0.06
     Colonel
    -0.06
    POSITIVE LOGITS
    (theta
    0.07
     νεφοκάλυψης
    0.07
    922
    0.07
    /model
    0.07
     freder
    0.07
    -TV
    0.07
    .sprite
    0.06
    Ranked
    0.06
    booking
    0.06
    .ReactNode
    0.06
    Act Density 0.006%

    No Known Activations