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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Multiple
    -0.07
     differing
    -0.07
    Aside
    -0.07
    પ
    -0.06
    <main
    -0.06
     aides
    -0.06
     commemor
    -0.06
    .readValue
    -0.06
    ई
    -0.06
    早早
    -0.06
    POSITIVE LOGITS
    hell
    0.08
     brakes
    0.07
    (stypy
    0.07
     Lid
    0.07
     alarmed
    0.07
    פורט
    0.07
    ution
    0.07
    stå
    0.07
    社会保障
    0.07
    艚
    0.07
    Act Density 0.001%

    No Known Activations