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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Davidson
    -0.07
    Pattern
    -0.07
     Force
    -0.07
    _dev
    -0.07
    Dev
    -0.06
    classifier
    -0.06
    _counts
    -0.06
     Cheng
    -0.06
     DB
    -0.06
    -rock
    -0.06
    POSITIVE LOGITS
     fourth
    0.06
    คร
    0.06
     unread
    0.06
     możli
    0.06
    (fabs
    0.06
     случ
    0.06
     closely
    0.06
     香港
    0.06
    ันวาคม
    0.06
    ayaran
    0.06
    Act Density 0.290%

    No Known Activations