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

    Neuronpedia

    INDEX
    Explanations

    examples or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.59
    j
    0.57
     ۵
    0.53
    5
    0.53
    ۰
    0.52
    s
    0.51
     다양한
    0.48
    4
    0.48
     Expectations
    0.48
     hearty
    0.48
    POSITIVE LOGITS
    感が
    0.45
    âni
    0.45
    劻
    0.43
    埒
    0.39
     కల
    0.39
    饪
    0.39
    敚
    0.39
    Salman
    0.38
    OLI
    0.38
     socialista
    0.38
    Act Density 0.000%

    No Known Activations