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

    Neuronpedia

    INDEX
    Explanations

    legal protection and authenticity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     November
    0.55
     September
    0.54
     January
    0.52
     Marketing
    0.51
     June
    0.50
     Market
    0.49
    0.49
     December
    0.49
     October
    0.48
     Ruby
    0.47
    POSITIVE LOGITS
    protect
    0.63
    protective
    0.60
     safeguards
    0.55
     protecting
    0.54
     protects
    0.54
    ป้องกัน
    0.53
    genuine
    0.53
    prote
    0.52
    Prote
    0.52
     schützen
    0.51
    Act Density 0.012%

    No Known Activations