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

    Neuronpedia

    INDEX
    Explanations

    differential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     `'
    -0.07
     đoàn
    -0.06
    atLng
    -0.06
     zij
    -0.06
    인지
    -0.06
     deneyim
    -0.06
    تیجه
    -0.06
     반
    -0.06
     Compute
    -0.06
     representation
    -0.06
    POSITIVE LOGITS
     differential
    0.08
     فر
    0.07
     TLabel
    0.07
    อน
    0.07
    -chevron
    0.07
     IPv
    0.07
    _dem
    0.06
     Differential
    0.06
     mysteries
    0.06
    )</
    0.06
    Act Density 0.008%

    No Known Activations