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
     flashy
    -0.06
     Bus
    -0.06
    sí
    -0.06
     lept
    -0.06
     Timing
    -0.06
    -door
    -0.06
     overnight
    -0.06
     ihm
    -0.06
    Carol
    -0.06
    090
    -0.06
    POSITIVE LOGITS
    ु�
    0.07
    ouflage
    0.06
    ěla
    0.06
    collection
    0.06
    asename
    0.06
     Ан
    0.06
     odmít
    0.06
     hrd
    0.06
    μενο
    0.06
     ἀ
    0.06
    Act Density 0.001%

    No Known Activations