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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Гуляць
    0.44
    逘
    0.42
    艐
    0.40
    ="")
    0.40
    ové
    0.40
    烪
    0.39
    购买
    0.39
    篒
    0.39
    த்தை
    0.38
    嘊
    0.38
    POSITIVE LOGITS
     mechanistic
    0.35
     nonfiction
    0.35
     marion
    0.35
     ples
    0.34
     titular
    0.33
     dainty
    0.33
     conversa
    0.33
     Mah
    0.33
     demurrer
    0.33
     flavorful
    0.33
    Act Density 0.000%

    No Known Activations