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

    Neuronpedia

    INDEX
    Explanations

    errors and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maraming
    0.64
     ngayon
    0.62
    EXIST
    0.60
    จุบัน
    0.60
    FindingsRequest
    0.59
     situational
    0.59
    śla
    0.59
     ہمیشہ
    0.59
    現在は
    0.59
     להיות
    0.58
    POSITIVE LOGITS
     installing
    2.13
     selecting
    2.11
     designing
    1.98
     deploying
    1.91
     trying
    1.89
     accessing
    1.89
     administering
    1.88
     transporting
    1.86
     assembling
    1.82
     conducting
    1.82
    Act Density 0.306%

    No Known Activations