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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ting
    0.74
    Liquid
    0.69
    penny
    0.68
    Lib
    0.68
     accessori
    0.67
    परि
    0.67
    SIZE
    0.66
    sized
    0.65
     sytu
    0.65
    Cet
    0.64
    POSITIVE LOGITS
     natural
    0.72
    ยม
    0.71
     slowest
    0.68
    у
    0.65
     У
    0.64
     God
    0.64
     huh
    0.63
    У
    0.62
     beauty
    0.61
     URL
    0.61
    Act Density 0.136%

    No Known Activations