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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prevalent
    0.62
     confound
    0.61
     proliferating
    0.60
     deriving
    0.56
     tok
    0.55
     derived
    0.55
     derive
    0.54
     proliferate
    0.54
     உதவுக
    0.53
    ங்குக
    0.53
    POSITIVE LOGITS
    th
    1.27
     ቀን
    1.01
     तारीख
    0.99
     noon
    0.95
     scorso
    0.95
     তারিখে
    0.94
     Noon
    0.93
    న
    0.91
     తేదీ
    0.91
    日
    0.90
    Act Density 0.103%

    No Known Activations