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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "a
    -0.08
    Woman
    -0.07
    .high
    -0.07
    :a
    -0.06
    "A
    -0.06
    encial
    -0.06
    eten
    -0.06
     بی
    -0.06
    改变
    -0.06
    ----------
    -0.06
    POSITIVE LOGITS
     Skyl
    0.07
    )+
    0.07
    _bottom
    0.06
     фай
    0.06
     rendition
    0.06
     ago
    0.06
    ्रथ
    0.06
     تاث
    0.06
     stata
    0.06
    owns
    0.06
    Act Density 0.006%

    No Known Activations