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

    Neuronpedia

    INDEX
    Explanations

    service database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alligator
    0.49
    tní
    0.45
     smother
    0.44
    frigerator
    0.43
    定番
    0.43
    न्दे
    0.43
     workman
    0.43
    ಡಿ
    0.43
     snappy
    0.43
     clamp
    0.42
    POSITIVE LOGITS
     Ethn
    0.50
    神经
    0.45
     Ethics
    0.45
    ברה
    0.45
    图书馆
    0.42
     ethn
    0.41
     Gesundheit
    0.40
    świad
    0.40
    Ethn
    0.40
     Enzym
    0.39
    Act Density 0.000%

    No Known Activations