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

    Neuronpedia

    INDEX
    Explanations

    entity and its description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    磴
    0.54
    imetry
    0.50
    ignez
    0.50
    लिये
    0.50
    getRedTeam
    0.50
    ሳሪያ
    0.49
    ๔
    0.48
    gleichen
    0.48
    ലോക
    0.48
     automatique
    0.48
    POSITIVE LOGITS
     Германия
    0.44
    фф
    0.44
     কেন্দ্র
    0.43
     NEA
    0.41
     yapt
    0.40
     фигуры
    0.40
     सीनियर
    0.40
     मैं
    0.40
    Edd
    0.40
     кто
    0.39
    Act Density 0.003%

    No Known Activations