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

    Neuronpedia

    INDEX
    Explanations

    objects and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AMBI
    0.46
    濾
    0.45
    謗
    0.44
     ಕಡಿಮೆ
    0.44
    ITING
    0.43
    optimized
    0.41
     Purchased
    0.41
     बर्बाद
    0.41
     unbear
    0.40
    yte
    0.40
    POSITIVE LOGITS
    Shoes
    0.44
    Chef
    0.42
    helps
    0.41
     chef
    0.40
    Help
    0.40
     shoes
    0.39
     যিনি
    0.39
     professeur
    0.39
     entrenador
    0.39
     você
    0.39
    Act Density 0.002%

    No Known Activations