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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Segment
    -0.08
     yıl
    -0.07
     trả
    -0.06
    (builder
    -0.06
    Tuple
    -0.06
     contrario
    -0.06
    .exception
    -0.06
    scaled
    -0.06
     вред
    -0.06
     fart
    -0.06
    POSITIVE LOGITS
     peg
    0.06
    School
    0.06
    /top
    0.06
     sc
    0.06
     kém
    0.06
     fl
    0.06
    콜걸
    0.06
     dàng
    0.06
    งท
    0.06
    leen
    0.06
    Act Density 0.274%

    No Known Activations