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

    Neuronpedia

    INDEX
    Explanations

    Searching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bq
    -0.07
     Naturally
    -0.06
     Archer
    -0.06
    .sem
    -0.06
    Vý
    -0.06
     disadvantages
    -0.06
     setter
    -0.06
     Ά
    -0.06
     bad
    -0.06
    Yaw
    -0.06
    POSITIVE LOGITS
    [:
    0.07
    frequency
    0.06
     antibiotics
    0.06
     pudd
    0.06
    จำนวน
    0.06
    dığı
    0.06
     غیر
    0.06
    conduct
    0.06
    (float
    0.06
    能力
    0.06
    Act Density 0.002%

    No Known Activations