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
     οργ
    -0.07
    .g
    -0.07
     озна
    -0.07
    BitFields
    -0.07
    -feature
    -0.06
     проти
    -0.06
     اسر
    -0.06
     Поль
    -0.06
     ambigu
    -0.06
    DidEnter
    -0.06
    POSITIVE LOGITS
    arro
    0.07
     pued
    0.07
    าผ
    0.06
    .simple
    0.06
    Order
    0.06
     Royal
    0.06
     stopping
    0.06
    ori
    0.06
    .pol
    0.06
     소
    0.06
    Act Density 0.003%

    No Known Activations