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

    Neuronpedia

    INDEX
    Explanations

    mb abbreviations and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Providing
    0.41
     specifying
    0.40
    Overflow
    0.40
    シス
    0.39
     Preparation
    0.39
    Fully
    0.38
    Use
    0.38
    Preparation
    0.38
     Giving
    0.38
     प्रिपरेशन
    0.38
    POSITIVE LOGITS
     mb
    0.63
    assador
    0.61
     amb
    0.57
     emb
    0.57
     MB
    0.57
     Mb
    0.57
     المب
    0.57
     Amb
    0.53
     ambush
    0.53
     एमबी
    0.53
    Act Density 0.017%

    No Known Activations