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

    Neuronpedia

    INDEX
    Explanations

    addiction, physical, mass, display

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emphasises
    0.42
     trycatch
    0.41
     summarize
    0.41
     summarizes
    0.40
    ადგენ
    0.40
     summarise
    0.39
     summarised
    0.39
     emphasise
    0.39
     peraturan
    0.39
     mercantil
    0.38
    POSITIVE LOGITS
     sát
    0.40
     emptying
    0.40
     kiire
    0.39
    所谓的
    0.38
     thorny
    0.36
     inefficiency
    0.35
     rápida
    0.35
    בק
    0.35
    清理
    0.35
     Calabria
    0.35
    Act Density 0.000%

    No Known Activations