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

    Neuronpedia

    INDEX
    Explanations

    Model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LG
    -0.07
     καθ
    -0.07
    LU
    -0.06
    Transformer
    -0.06
     sábado
    -0.06
    .recv
    -0.06
     LAN
    -0.06
     Cummings
    -0.06
     Ao
    -0.06
    Marca
    -0.06
    POSITIVE LOGITS
    whether
    0.07
    ishing
    0.07
    人民共和国
    0.06
     exercising
    0.06
     healthier
    0.06
     fighting
    0.06
    irie
    0.06
     ARTICLE
    0.06
    شتر
    0.06
    …"↵↵
    0.06
    Act Density 0.002%

    No Known Activations