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

    Neuronpedia

    INDEX
    Explanations

    code snippets and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    1.18
     yerden
    1.18
     successors
    1.17
    enden
    1.14
    +,
    1.12
     বাড়িতে
    1.12
    𝗹
    1.10
    unction
    1.09
    到时候
    1.09
    ┙
    1.08
    POSITIVE LOGITS
    bibnamefont
    1.11
    れる
    1.06
    CIT
    1.05
    packaged
    1.04
    Shader
    1.04
    τοι
    1.03
    膚
    1.02
    مح
    1.02
    れた
    1.01
     باسم
    1.00
    Act Density 0.000%

    No Known Activations