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

    Neuronpedia

    INDEX
    Explanations

    identifying potential odors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mechanism
    0.47
     sucess
    0.46
     version
    0.45
    i
    0.44
     verdadero
    0.44
     وبي
    0.44
     vô
    0.43
     HAVING
    0.43
     for
    0.43
     test
    0.43
    POSITIVE LOGITS
     絵
    0.51
    黼
    0.50
    捙
    0.49
    issors
    0.48
    ukka
    0.48
    ുക
    0.48
    applique
    0.48
     Manik
    0.47
     सीतारमण
    0.47
    ängel
    0.47
    Act Density 0.000%

    No Known Activations