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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traf
    -0.06
    .hxx
    -0.06
     Putin
    -0.06
    죽
    -0.06
     caffeine
    -0.06
     Sweep
    -0.06
    _pool
    -0.06
    legs
    -0.06
    폐
    -0.06
     nêu
    -0.06
    POSITIVE LOGITS
    Medical
    0.07
    ENCES
    0.07
    ORIES
    0.07
     sağlan
    0.07
    िक
    0.06
    OO
    0.06
    Whats
    0.06
    placements
    0.06
    완료
    0.06
    üyoruz
    0.06
    Act Density 0.111%

    No Known Activations