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

    Neuronpedia

    INDEX
    Explanations

    JavaFX UI components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frumo
    0.44
    primary
    0.40
    存档
    0.39
    beautiful
    0.39
     排
    0.39
    坯
    0.39
    Beautiful
    0.38
     عليه
    0.38
    凧
    0.38
     pięk
    0.38
    POSITIVE LOGITS
     fx
    0.55
    fx
    0.52
     FX
    0.50
    TableCell
    0.46
    getItems
    0.44
    costcenter
    0.39
    Fx
    0.38
     cell
    0.37
     LOOK
    0.37
    গঠনিক
    0.36
    Act Density 0.001%

    No Known Activations