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

    Neuronpedia

    INDEX
    Explanations

    building elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     среднем
    0.40
    Econom
    0.40
    pulse
    0.39
     मैट्र
    0.39
    MoodAnalyser
    0.38
     बुला
    0.38
    utilise
    0.38
    kost
    0.37
     сюжет
    0.37
    ør
    0.36
    POSITIVE LOGITS
     Visiting
    0.48
     visiting
    0.45
     mentioning
    0.42
     Coordinates
    0.41
    Visiting
    0.41
     coordinates
    0.40
     mentions
    0.40
     once
    0.39
     recommending
    0.39
     squint
    0.39
    Act Density 0.000%

    No Known Activations