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

    Neuronpedia

    INDEX
    Explanations

    Intel Core CPUs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guidance
    0.63
     guía
    0.60
     मार्गदर्शन
    0.60
    ガイド
    0.59
     guid
    0.58
     Guidance
    0.56
     guide
    0.55
     GUIDE
    0.55
     guia
    0.54
     GUID
    0.53
    POSITIVE LOGITS
     దూ
    0.39
    ma
    0.38
    isten
    0.38
    implement
    0.37
    irl
    0.37
    Trump
    0.36
    volatile
    0.36
    Brexit
    0.36
    см
    0.36
    chlor
    0.36
    Act Density 0.002%

    No Known Activations