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

    Neuronpedia

    INDEX
    Explanations

    tangents and circles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inge
    -0.08
    ,
    -0.07
     stored
    -0.07
    stored
    -0.07
     defines
    -0.07
     etc
    -0.07
     auto
    -0.07
     thu
    -0.07
    auto
    -0.07
     Só
    -0.07
    POSITIVE LOGITS
     Neither
    0.09
     picturesque
    0.08
     silhou
    0.08
     దర్శ
    0.08
     extreme
    0.08
     располож
    0.08
    共和国
    0.08
    Neither
    0.08
    vereiro
    0.08
     ekran
    0.08
    Act Density 0.015%

    No Known Activations