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

    Neuronpedia

    INDEX
    Explanations

    code/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gay
    -0.06
     drawn
    -0.06
    نى
    -0.06
     relies
    -0.06
    uele
    -0.06
     Clay
    -0.06
    pite
    -0.06
     celebrated
    -0.06
    iore
    -0.06
    teki
    -0.06
    POSITIVE LOGITS
     threats
    0.06
     adopting
    0.06
    _logger
    0.06
     đ
    0.06
     intermedi
    0.06
     Ops
    0.06
     Ps
    0.06
     způsob
    0.06
    servers
    0.06
     yüksek
    0.06
    Act Density 0.000%

    No Known Activations