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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सुप्रीम
    0.37
     moniker
    0.36
     staffers
    0.36
     عندما
    0.35
     ஜோ
    0.35
     आवंट
    0.35
     बदनाम
    0.35
     kiedy
    0.35
     सीबीएसई
    0.35
     restante
    0.34
    POSITIVE LOGITS
     any
    0.74
     such
    0.71
     specified
    0.62
    any
    0.62
    such
    0.61
    specified
    0.55
     такие
    0.54
     qualquer
    0.53
     orice
    0.53
     cualquier
    0.51
    Act Density 0.000%

    No Known Activations