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

    Neuronpedia

    INDEX
    Explanations

    how much/many/lucky/grateful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எது
    0.43
     Distinction
    0.42
     distinction
    0.41
     Où
    0.41
    XmlApplication
    0.40
     Where
    0.40
    では
    0.39
     Где
    0.39
    哪里
    0.38
     Donde
    0.38
    POSITIVE LOGITS
     얼마나
    1.29
     насколько
    1.26
     how
    1.19
     combien
    1.06
     quanto
    1.05
     কতটা
    1.02
     koliko
    1.02
    多么
    1.02
     hoeveel
    0.99
     cuánto
    0.97
    Act Density 0.009%

    No Known Activations