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

    Neuronpedia

    INDEX
    Explanations

    code and mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciencias
    0.49
    лаго
    0.47
     Sql
    0.44
     welder
    0.44
     commandment
    0.44
     techs
    0.43
     Ото
    0.43
     меку
    0.42
     chromed
    0.42
     Dependency
    0.42
    POSITIVE LOGITS
     تھیں
    0.39
    是非
    0.39
    䏼
    0.39
    尽可能
    0.38
    allist
    0.38
    ↵↵↵
    0.37
    othermic
    0.37
    적인
    0.36
    itone
    0.36
    isiert
    0.36
    Act Density 0.018%

    No Known Activations