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

    Neuronpedia

    INDEX
    Explanations

    error handling in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '>";
    0.40
    滟
    0.40
    gramModel
    0.39
    营造
    0.38
     terraz
    0.38
    OMBRE
    0.38
    ówno
    0.38
    🚱
    0.37
    Kul
    0.37
    Muito
    0.37
    POSITIVE LOGITS
     Pair
    0.41
    ht
    0.35
     Steering
    0.35
     contributes
    0.34
     Airline
    0.34
     })
    0.33
     Insurance
    0.33
     would
    0.33
     President
    0.33
     EL
    0.33
    Act Density 0.050%

    No Known Activations