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

    Neuronpedia

    INDEX
    Explanations

    I'm still under development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     કારણે
    0.45
    uerre
    0.45
     samt
    0.44
     massif
    0.43
    डम
    0.43
     பர
    0.43
     Realme
    0.42
     Gentiles
    0.42
    Borderless
    0.42
     ማለት
    0.42
    POSITIVE LOGITS
     please
    0.55
     don
    0.52
     PLEASE
    0.45
    되면
    0.45
     Veuillez
    0.44
    please
    0.43
     veuillez
    0.43
    you
    0.43
    쥔
    0.41
     Please
    0.41
    Act Density 0.001%

    No Known Activations