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

    Neuronpedia

    INDEX
    Explanations

    try...except blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spre
    0.67
    sprach
    0.64
     soggiorno
    0.64
     Sar
    0.63
    バック
    0.63
    ˢ
    0.62
    iffy
    0.62
     backdrop
    0.61
    fa
    0.60
     sæ
    0.60
    POSITIVE LOGITS
     Buses
    0.70
    ደን
    0.63
    inator
    0.62
     плане
    0.60
     verific
    0.60
    Bytes
    0.59
     Verification
    0.59
    Wires
    0.58
     মাংস
    0.58
     അവസാന
    0.58
    Act Density 0.132%

    No Known Activations