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

    Neuronpedia

    INDEX
    Explanations

    explaining why or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fue
    0.43
    早在
    0.43
     नेता
    0.42
     intensify
    0.42
    ے۔
    0.41
    odh
    0.41
     optimizes
    0.41
     logró
    0.40
     complejos
    0.40
    战略
    0.40
    POSITIVE LOGITS
     sour
    0.38
     anisotropic
    0.38
     fold
    0.38
     table
    0.37
    niejsze
    0.37
     folded
    0.37
     नम
    0.35
     proportion
    0.35
    Commands
    0.35
    REST
    0.35
    Act Density 0.003%

    No Known Activations