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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лены
    -0.07
     VN
    -0.07
    624
    -0.06
    -largest
    -0.06
    aporation
    -0.06
     cinemat
    -0.06
    เช
    -0.06
    ัฒ
    -0.06
    ��제
    -0.06
     BH
    -0.06
    POSITIVE LOGITS
    operators
    0.07
     نک
    0.07
    نویس
    0.07
    .logic
    0.06
    قط
    0.06
    ackBar
    0.06
     увид
    0.06
    ああ
    0.06
    tracks
    0.06
     voir
    0.06
    Act Density 0.054%

    No Known Activations