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

    Neuronpedia

    INDEX
    Explanations

    calculations involving units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⮚
    0.47
    𝗕
    0.45
    spielen
    0.43
    菓
    0.43
     FLORIDA
    0.43
    🛵
    0.42
    شاركة
    0.42
    资本
    0.41
    uscany
    0.41
     중요한
    0.41
    POSITIVE LOGITS
     ps
    0.40
    ↵
    0.39
     speed
    0.38
     SA
    0.38
    -
    0.37
     light
    0.36
     hear
    0.36
     sm
    0.35
     ba
    0.35
    id
    0.35
    Act Density 0.006%

    No Known Activations