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

    Neuronpedia

    INDEX
    Explanations

    months and days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    겟
    0.42
    किया
    0.41
     calibrate
    0.38
    äft
    0.37
     সঙ্গী
    0.37
    álie
    0.37
     veins
    0.36
    emps
    0.36
     planes
    0.35
     inserts
    0.35
    POSITIVE LOGITS
     adalah
    0.49
    =[],
    0.49
     là
    0.47
     Boltzmann
    0.41
     Caj
    0.41
     violência
    0.40
    =[]
    0.40
     Là
    0.39
    ພວກເຮົາ
    0.39
    में
    0.38
    Act Density 0.001%

    No Known Activations