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

    Neuronpedia

    INDEX
    Explanations

    used as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दुकानें
    0.50
     قرب
    0.47
    shareButton
    0.47
     ಸರಿಯ
    0.47
    osevelt
    0.47
    äuser
    0.47
     حوصل
    0.47
    yeri
    0.47
    ੩
    0.47
    btnPrint
    0.46
    POSITIVE LOGITS
    0.49
    ]$,
    0.47
    )
    0.47
    Z
    0.47
    Design
    0.46
    Trust
    0.45
    Dis
    0.44
    ט
    0.44
    AV
    0.44
     Components
    0.44
    Act Density 0.000%

    No Known Activations