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

    Neuronpedia

    INDEX
    Explanations

    hesitant, clarity, damp, quiet, trustworthiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eq
    0.55
     výkon
    0.50
     konfl
    0.47
     algod
    0.46
     anys
    0.46
     attribut
    0.46
     enkelt
    0.46
    iv
    0.46
    ogener
    0.45
    ضاء
    0.45
    POSITIVE LOGITS
    chini
    0.46
     beautiful
    0.45
     flavorful
    0.45
    U
    0.45
    тисти
    0.43
    ところに
    0.43
     commemorative
    0.43
     Christopher
    0.42
     Dele
    0.41
    ື່ອງ
    0.41
    Act Density 0.001%

    No Known Activations