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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WORLD
    -0.07
    HTTP
    -0.06
    cession
    -0.06
     moderation
    -0.06
    umped
    -0.06
     showers
    -0.06
    ilim
    -0.06
    ông
    -0.06
     тверд
    -0.06
    егодня
    -0.06
    POSITIVE LOGITS
    ριστ
    0.06
    んで
    0.06
    (日
    0.06
     Ή
    0.06
    .pub
    0.06
     ACK
    0.06
     NumberOf
    0.06
     ию
    0.06
    १
    0.06
     Collect
    0.06
    Act Density 0.002%

    No Known Activations