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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    र्तन
    -0.08
     Phantom
    -0.07
    ற்று
    -0.07
     friend's
    -0.07
     lớp
    -0.07
     peças
    -0.07
     rä
    -0.07
    ற்ற
    -0.07
     nenhum
    -0.07
     갑
    -0.07
    POSITIVE LOGITS
     shorten
    0.15
     shortened
    0.13
     shorter
    0.12
     shortening
    0.12
    简称
    0.11
     saja
    0.11
    简
    0.10
     shorthand
    0.10
     sahaja
    0.10
     abbreviated
    0.09
    Act Density 0.034%

    No Known Activations