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

    Neuronpedia

    INDEX
    Explanations

    example phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perv
    0.46
     gestión
    0.43
    urgy
    0.42
     zostały
    0.41
    ంచు
    0.40
     permeates
    0.39
     mir
    0.38
     parchment
    0.37
     endured
    0.37
     macromolecules
    0.37
    POSITIVE LOGITS
    например
    1.03
    例えば
    1.02
     например
    1.01
     Например
    1.01
     Örneğin
    0.98
     esempio
    0.98
     예를
    0.98
    比如
    0.96
     ejemplo
    0.96
     example
    0.96
    Act Density 0.426%

    No Known Activations