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

    Neuronpedia

    INDEX
    Explanations

    abstract spiritual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soldered
    0.41
    της
    0.40
    stories
    0.40
    archer
    0.39
    δήποτε
    0.38
    りに
    0.38
     resistance
    0.36
    Fern
    0.36
    一定是
    0.36
    乙
    0.36
    POSITIVE LOGITS
     Pampl
    0.40
    ền
    0.38
    iong
    0.38
     padres
    0.37
     IAEA
    0.37
    ídio
    0.37
    কেন্দ্র
    0.37
     MLP
    0.37
    畊
    0.37
     অস্বীকার
    0.36
    Act Density 0.000%

    No Known Activations