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

    Neuronpedia

    INDEX
    Explanations

    consequential abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভাবনা
    0.42
     botella
    0.41
     aflat
    0.41
     Retail
    0.41
     fructose
    0.41
     chipset
    0.40
     hochwertige
    0.40
     expectativas
    0.39
     hiko
    0.39
     adware
    0.39
    POSITIVE LOGITS
     whispered
    0.46
     mingled
    0.41
     ஏற்பட்ட
    0.41
    vollen
    0.41
     flung
    0.39
     ஏற்பட்டு
    0.39
    fully
    0.38
    FULLY
    0.38
     وفا
    0.37
    shown
    0.37
    Act Density 0.009%

    No Known Activations