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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twice
    -0.08
    span
    -0.07
     inward
    -0.07
     AWS
    -0.07
     pulls
    -0.07
     Lease
    -0.07
     sprung
    -0.07
     tile
    -0.07
    ê
    -0.06
    ueur
    -0.06
    POSITIVE LOGITS
     člově
    0.07
    력이
    0.06
     bx
    0.06
    .Center
    0.06
     کاهش
    0.06
     cfg
    0.06
    osoph
    0.06
    .coeff
    0.06
     živ
    0.06
    .AutoField
    0.06
    Act Density 0.031%

    No Known Activations