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

    Neuronpedia

    INDEX
    Explanations

    parentheses and semicolons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jede
    1.15
     passable
    1.13
    zelfde
    1.10
    mals
    1.04
    "+"|".
    1.02
    anded
    1.01
    수상
    1.01
     trasfer
    1.01
    ільки
    1.00
     wesentlich
    0.99
    POSITIVE LOGITS
    ट्स
    1.50
    𝒍
    1.29
     With
    1.28
    ↵↵
    1.25
     That
    1.24
     By
    1.23
    𝒊
    1.23
    erving
    1.22
     OEMs
    1.21
    𝐥
    1.21
    Act Density 0.139%

    No Known Activations