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

    Neuronpedia

    INDEX
    Explanations

    Descriptive phrases with &

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clk
    0.43
    传来
    0.43
     Clamp
    0.41
     Bracelet
    0.41
     PREVENTION
    0.40
     Cycling
    0.40
     Triumph
    0.39
     prévention
    0.39
     Mirza
    0.38
     Knows
    0.38
    POSITIVE LOGITS
    status
    0.46
    ance
    0.44
     hẳn
    0.41
     status
    0.40
    Status
    0.40
     molded
    0.38
     spiked
    0.37
    Pixels
    0.37
     ineligible
    0.37
     charged
    0.36
    Act Density 0.005%

    No Known Activations