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

    Neuronpedia

    INDEX
    Explanations

    legal and official contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nostre
    0.50
     numpy
    0.50
     یا
    0.50
     define
    0.49
     multiplicative
    0.49
     mūsų
    0.47
     generalize
    0.46
     initialize
    0.46
     your
    0.45
     configure
    0.45
    POSITIVE LOGITS
     Officials
    0.70
    据悉
    0.64
     Supporters
    0.61
     당시
    0.60
     officials
    0.59
     अधिकारियों
    0.59
     reportedly
    0.57
     Apparently
    0.55
     supporters
    0.55
    उन्होंने
    0.55
    Act Density 0.003%

    No Known Activations