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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     البي
    -0.07
     �
    -0.07
     gönder
    -0.06
    eland
    -0.06
    ười
    -0.06
    avar
    -0.06
     eğer
    -0.06
     archival
    -0.06
    .seq
    -0.06
     triples
    -0.06
    POSITIVE LOGITS
     maintained
    0.06
    .Network
    0.06
     resort
    0.06
     января
    0.06
     Uni
    0.06
     s
    0.06
    StateChanged
    0.06
    ард
    0.06
     ±
    0.06
     mín
    0.06
    Act Density 0.000%

    No Known Activations