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

    Neuronpedia

    INDEX
    Explanations

    visual scene description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कैटेगरी
    0.42
     जेव्हा
    0.40
     aceptas
    0.39
     считает
    0.39
     nonprofits
    0.36
     eficiencia
    0.36
     learnings
    0.35
     infecciones
    0.35
     inability
    0.35
     دوسروں
    0.34
    POSITIVE LOGITS
     copyspace
    0.55
     sfondo
    0.52
     glistening
    0.52
     crouching
    0.50
    背景
    0.50
     reddish
    0.49
     blurred
    0.49
     billowing
    0.49
     scene
    0.49
    画面
    0.49
    Act Density 0.518%

    No Known Activations