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

    Neuronpedia

    INDEX
    Explanations

    One

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     read
    -0.08
    ак
    -0.07
     softer
    -0.07
     rằng
    -0.06
     reviewing
    -0.06
     Crawford
    -0.06
     pray
    -0.06
    ansion
    -0.06
     reads
    -0.06
     advancement
    -0.06
    POSITIVE LOGITS
     dolu
    0.07
     Colt
    0.06
    나는
    0.06
    üslü
    0.06
    (fe
    0.06
     UPS
    0.06
    .ElementAt
    0.06
     jb
    0.06
    [__
    0.06
    _NOP
    0.06
    Act Density 0.012%

    No Known Activations