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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impres
    -0.08
    刊
    -0.08
    <Device
    -0.08
    রম
    -0.08
    ্যের
    -0.08
     ingestion
    -0.08
     accumulation
    -0.08
     sammen
    -0.08
     spiritual
    -0.08
    ýs
    -0.07
    POSITIVE LOGITS
     opponents
    0.11
     Gegner
    0.09
     defeated
    0.09
     поведения
    0.09
     opponent
    0.09
    _traits
    0.08
     personalities
    0.08
     behavior
    0.08
     comportement
    0.08
    zko
    0.08
    Act Density 0.004%

    No Known Activations