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

    Neuronpedia

    INDEX
    Explanations

    selected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aph
    -0.07
    瓻
    -0.07
     Kush
    -0.07
    อาการ
    -0.07
     bust
    -0.07
    쮜
    -0.07
    无忧
    -0.06
     khả
    -0.06
    .Batch
    -0.06
    حاضر
    -0.06
    POSITIVE LOGITS
    ICE
    0.07
    부
    0.07
     Bands
    0.07
     timing
    0.07
     theme
    0.07
    (Line
    0.06
    赁
    0.06
    ביקור
    0.06
    Key
    0.06
     DECL
    0.06
    Act Density 0.002%

    No Known Activations