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

    Neuronpedia

    INDEX
    Explanations

    tourism and healthcare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     परमा
    0.40
    стре
    0.39
    мах
    0.39
    ڈر
    0.39
    гло
    0.38
     اے
    0.38
    гү
    0.38
    塚
    0.38
    굴
    0.37
    ங்கை
    0.36
    POSITIVE LOGITS
    newL
    0.41
     Trab
    0.41
    lebr
    0.40
    ْس
    0.39
    esta
    0.39
     Gas
    0.38
    䫒
    0.38
     pagare
    0.38
    новременно
    0.38
     traw
    0.37
    Act Density 0.001%

    No Known Activations