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

    Neuronpedia

    INDEX
    Explanations

    leading to victory or success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     learned
    0.38
    esters
    0.36
    ern
    0.35
    ുകളെ
    0.35
     lost
    0.35
     विक
    0.35
    出来
    0.35
     understood
    0.34
    Traversal
    0.34
     বিপর
    0.34
    POSITIVE LOGITS
     past
    0.52
     PAST
    0.49
    到
    0.47
    past
    0.46
     Past
    0.44
    煅
    0.42
     إلى
    0.42
    ফার
    0.40
     trough
    0.40
     到
    0.39
    Act Density 0.006%

    No Known Activations