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

    Neuronpedia

    INDEX
    Explanations

    words ending in ies and non

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    culus
    0.39
    Sand
    0.38
     terraces
    0.38
    Dane
    0.38
    嵋
    0.38
    ством
    0.37
    Michelle
    0.37
     Schaus
    0.37
     bouquets
    0.37
     Capabilities
    0.36
    POSITIVE LOGITS
     轻
    0.38
    祅
    0.38
     ఆరోగ్య
    0.36
     коммер
    0.36
     বিনা
    0.36
    ιν
    0.35
     አገልግሎ
    0.35
     herm
    0.34
     কন্যা
    0.34
     Jazeera
    0.34
    Act Density 0.000%

    No Known Activations