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

    Neuronpedia

    INDEX
    Explanations

    punctuation followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     without
    0.51
     tanpa
    0.47
     zonder
    0.43
     uden
    0.43
     WITHOUT
    0.42
    無需
    0.42
    毫不
    0.40
     ohne
    0.39
     без
    0.39
     بغیر
    0.39
    POSITIVE LOGITS
    而是
    0.94
     بلکه
    0.79
     बल्कि
    0.79
     nor
    0.74
     sondern
    0.72
     بلکہ
    0.71
     Instead
    0.71
     বরং
    0.70
    Instead
    0.68
    nor
    0.66
    Act Density 0.452%

    No Known Activations