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

    Neuronpedia

    INDEX
    Explanations

    wants/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _disconnect
    -0.07
    %.
    -0.07
     to
    -0.07
    应当
    -0.06
     mogelijk
    -0.06
     %.
    -0.06
     듯
    -0.06
     نوف
    -0.06
    正确
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    :D
    0.07
     produk
    0.07
    \Command
    0.06
     تکن
    0.06
     Identification
    0.06
     recommendation
    0.06
     Vocabulary
    0.06
    ahat
    0.06
    _DS
    0.06
     iş
    0.06
    Act Density 0.128%

    No Known Activations