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

    Neuronpedia

    INDEX
    Explanations

    Competition and feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Json
    -0.07
     Whereas
    -0.06
    .ToShort
    -0.06
     trailer
    -0.06
     {}↵↵
    -0.06
     thankfully
    -0.06
    (Device
    -0.06
     Pepper
    -0.06
    <LM
    -0.06
     PMC
    -0.06
    POSITIVE LOGITS
     tuyệt
    0.07
     çı
    0.06
    ulating
    0.06
    ंधन
    0.06
    erli
    0.06
    payment
    0.06
     marque
    0.06
    력
    0.06
    购买
    0.06
    .Refresh
    0.06
    Act Density 0.050%

    No Known Activations