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

    Neuronpedia

    INDEX
    Explanations

    Google Cloud and App

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drummond
    0.44
     EventEmitter
    0.43
     Scorpio
    0.42
     cardinals
    0.39
     analytics
    0.39
     জাতি
    0.38
     cervix
    0.38
     Draco
    0.38
     asthma
    0.38
     গভর্ন
    0.38
    POSITIVE LOGITS
    dat
    0.61
     dat
    0.58
     App
    0.55
     Dat
    0.55
     Cloud
    0.55
    Dat
    0.53
    Cloud
    0.52
    Persistent
    0.52
    Blob
    0.49
     Blob
    0.48
    Act Density 0.008%

    No Known Activations