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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    syntax
    -0.07
     ｲ
    -0.07
     related
    -0.07
     CONTROL
    -0.07
     Worksheet
    -0.07
     COMMIT
    -0.06
    Duplicates
    -0.06
     comparer
    -0.06
     auditing
    -0.06
    ově
    -0.06
    POSITIVE LOGITS
     forg
    0.06
     Çok
    0.06
    LEAN
    0.06
    ribly
    0.06
     Khan
    0.06
    Yang
    0.06
     Worker
    0.06
    واع
    0.06
    iffe
    0.06
     randint
    0.06
    Act Density 0.018%

    No Known Activations