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

    Neuronpedia

    INDEX
    Explanations

    and, punctuation, structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elabel
    0.44
    ହା
    0.42
     twofold
    0.42
    тель
    0.41
    alda
    0.41
     ñ
    0.40
    olist
    0.39
    afstand
    0.39
     confronts
    0.39
    obatan
    0.38
    POSITIVE LOGITS
    表達
    0.46
    丝毫
    0.44
    翼
    0.44
     terre
    0.43
    表达
    0.42
     twist
    0.41
     wewnętr
    0.40
    μου
    0.39
     Twist
    0.38
    耽
    0.38
    Act Density 4.447%

    No Known Activations