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

    Neuronpedia

    INDEX
    Explanations

    with or without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তথ্য
    0.32
     explanatory
    0.32
     தான்
    0.30
     आविष्कार
    0.30
    ค่อย
    0.30
     uppermost
    0.29
    렷
    0.29
     mainMenu
    0.29
    就可以了
    0.29
    श्यक
    0.28
    POSITIVE LOGITS
     with
    0.70
     without
    0.69
     using
    0.62
     avec
    0.62
     עם
    0.62
     WITH
    0.61
     với
    0.57
     без
    0.57
    without
    0.57
     utilizando
    0.57
    Act Density 0.672%

    No Known Activations