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

    Neuronpedia

    INDEX
    Explanations

    software configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aç
    -0.07
    tour
    -0.07
    읍
    -0.07
    ้าน
    -0.06
     teknoloj
    -0.06
    umn
    -0.06
    _models
    -0.06
     hole
    -0.06
     ssid
    -0.06
    Take
    -0.06
    POSITIVE LOGITS
     Production
    0.07
     "$(
    0.07
     shuffle
    0.07
    .joda
    0.06
    hetto
    0.06
     Cath
    0.06
     Logistics
    0.06
    embedding
    0.06
    bla
    0.06
     baud
    0.06
    Act Density 0.148%

    No Known Activations