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

    Neuronpedia

    INDEX
    Explanations

    explanations and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resets
    0.44
     idempot
    0.44
     decomposes
    0.43
     mortality
    0.42
     kotlin
    0.42
     pathophysiology
    0.42
     emergencies
    0.42
    校园
    0.42
     rescaling
    0.42
    지와
    0.41
    POSITIVE LOGITS
     अग्रणी
    0.47
     Shopping
    0.46
     relegated
    0.46
    ंसारी
    0.43
    Shopping
    0.42
     Realtors
    0.42
     Ти
    0.41
     coluna
    0.40
     dominante
    0.40
     वस्तू
    0.40
    Act Density 0.005%

    No Known Activations