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

    Neuronpedia

    INDEX
    Explanations

    time context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     زندگی
    0.46
    生活的
    0.45
     Belanda
    0.45
     tagName
    0.44
     habla
    0.44
     crée
    0.44
    违法
    0.41
     donné
    0.41
     ജീവിത
    0.41
    vita
    0.41
    POSITIVE LOGITS
    %=
    0.42
    Ма
    0.39
    FLO
    0.39
    }}+
    0.38
    CB
    0.38
     elongation
    0.38
    arp
    0.37
    殲
    0.37
    initely
    0.37
    smoothed
    0.37
    Act Density 0.000%

    No Known Activations