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

    Neuronpedia

    INDEX
    Explanations

    to help give the best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     setelah
    0.50
     після
    0.46
     Ha
    0.45
     После
    0.44
     dopo
    0.43
     然後
    0.42
     nakon
    0.42
     เมื่อ
    0.41
    Wenn
    0.41
     tecnologia
    0.41
    POSITIVE LOGITS
     maximise
    0.54
     maximize
    0.51
     further
    0.48
    更好地
    0.47
     gauge
    0.44
     better
    0.43
    最好
    0.43
     avoid
    0.43
     maximized
    0.42
     maximally
    0.42
    Act Density 0.097%

    No Known Activations