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

    Neuronpedia

    INDEX
    Explanations

    buyer personas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aktiv
    0.43
     vich
    0.40
    கன்
    0.38
     ধার
    0.38
    िलायंस
    0.38
    ToExp
    0.37
    ocarcinoma
    0.37
     dhan
    0.37
    uenza
    0.37
     bount
    0.37
    POSITIVE LOGITS
    י
    0.46
     airbags
    0.46
    :**
    0.45
    ologiques
    0.44
     भीती
    0.44
    ↵↵
    0.43
    rig
    0.43
     إ
    0.42
    ي
    0.41
    BT
    0.41
    Act Density 0.001%

    No Known Activations