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

    Neuronpedia

    INDEX
    Explanations

    electron density

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    à
    0.57
    ly
    0.57
    s
    0.54
    0
    0.54
    µ
    0.54
    ()).
    0.53
    d
    0.52
    9
    0.52
    very
    0.51
    ď
    0.51
    POSITIVE LOGITS
     PEOPLE
    0.61
     समर्थक
    0.59
     정보를
    0.58
     RECORDS
    0.58
     레
    0.55
     recipro
    0.55
     ಸ್ನೇ
    0.53
     コー
    0.53
     GUIDE
    0.52
     females
    0.51
    Act Density 0.011%

    No Known Activations