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

    Neuronpedia

    INDEX
    Explanations

    method or filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     House
    0.50
     Escal
    0.43
     Consultancy
    0.42
     Gi
    0.40
     del
    0.40
     dieser
    0.40
    ässä
    0.40
     इधर
    0.40
     অন্যতম
    0.39
     Bars
    0.39
    POSITIVE LOGITS
    ंसू
    0.45
    フィルター
    0.42
     méthode
    0.42
     메서
    0.41
     méthod
    0.41
     메소
    0.40
     gpu
    0.40
     methodological
    0.39
    メソッド
    0.38
     metodología
    0.38
    Act Density 0.000%

    No Known Activations