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

    Neuronpedia

    INDEX
    Explanations

    coordinating conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.57
     समुद्रा
    0.52
    :~
    0.52
    :...
    0.48
    crackers
    0.47
    fool
    0.46
    .:
    0.46
     कॅम्प
    0.46
    ᗰ
    0.45
    我就
    0.45
    POSITIVE LOGITS
     Additionally
    0.69
    ↵↵
    0.66
    ↵
    0.66
     Ayrıca
    0.64
     Inoltre
    0.61
     oraz
    0.61
    ↵↵↵
    0.56
     serta
    0.55
     همچنین
    0.55
     nonché
    0.55
    Act Density 0.050%

    No Known Activations