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

    Neuronpedia

    INDEX
    Explanations

    Lists of items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MICRO
    -0.07
    -)
    -0.06
    +)
    -0.06
     National
    -0.06
     ¬
    -0.06
    plant
    -0.06
     zv
    -0.06
     Î
    -0.06
    timing
    -0.06
    okers
    -0.06
    POSITIVE LOGITS
    .В
    0.07
    ��
    0.07
    。我
    0.07
    plt
    0.07
    .Many
    0.07
    axies
    0.06
    erged
    0.06
    ลล
    0.06
     extreme
    0.06
    ظر
    0.06
    Act Density 0.066%

    No Known Activations