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

    Neuronpedia

    INDEX
    Explanations

    caterpillars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Obrázky
    -0.07
    .--
    -0.06
    notes
    -0.06
    ,\↵
    -0.06
     deutschland
    -0.06
     MONEY
    -0.06
     nutzen
    -0.06
    -[
    -0.06
    Mayor
    -0.06
     pastor
    -0.06
    POSITIVE LOGITS
    pillar
    0.11
     cater
    0.08
     Spencer
    0.08
     placeholder
    0.07
     CG
    0.07
     αρι
    0.07
     میتوان
    0.07
     Spark
    0.07
    REGISTER
    0.07
    輪
    0.06
    Act Density 0.001%

    No Known Activations