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

    Neuronpedia

    INDEX
    Explanations

    hours of sunlight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vững
    0.52
     Помимо
    0.47
     OpenAI
    0.46
    AN
    0.45
    eban
    0.43
    izan
    0.42
    भाविक
    0.42
    D
    0.42
     Mesmo
    0.42
     বয়সী
    0.41
    POSITIVE LOGITS
     onder
    0.51
     to
    0.50
     areas
    0.48
     मे
    0.48
     agreements
    0.48
     во
    0.47
     murdering
    0.47
     verein
    0.46
    murder
    0.46
     hydrox
    0.46
    Act Density 0.000%

    No Known Activations