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

    Neuronpedia

    INDEX
    Explanations

    multiplication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    批
    -0.07
     Pilot
    -0.07
    𝑵
    -0.07
     sensitivity
    -0.07
     pad
    -0.07
     Capability
    -0.07
     MP
    -0.07
     Sponsored
    -0.06
     ft
    -0.06
    jp
    -0.06
    POSITIVE LOGITS
     comport
    0.07
    렉
    0.07
    름
    0.07
     العمر
    0.07
     szczegółowo
    0.07
     LOWER
    0.07
    .Embed
    0.06
    .LEADING
    0.06
     threesome
    0.06
     đức
    0.06
    Act Density 0.019%

    No Known Activations