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

    Neuronpedia

    INDEX
    Explanations

    outdated or out of sync

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     টে
    0.39
    তনাম
    0.38
    OPH
    0.36
    Dak
    0.36
    Ep
    0.36
    HttpFoundation
    0.35
    ستون
    0.35
     ucfirst
    0.35
    Ek
    0.34
     간
    0.34
    POSITIVE LOGITS
    dated
    0.77
    landish
    0.66
    sized
    0.66
     out
    0.61
    rag
    0.61
     outdated
    0.57
    rage
    0.55
    grown
    0.55
    out
    0.54
     Out
    0.54
    Act Density 0.010%

    No Known Activations