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

    Neuronpedia

    INDEX
    Explanations

    city and state names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     слегка
    0.37
     алкого
    0.36
     penso
    0.36
     sepenuhnya
    0.36
     lemongrass
    0.36
     alfabeto
    0.35
     должна
    0.35
     inteiro
    0.34
     sightseeing
    0.34
     populer
    0.34
    POSITIVE LOGITS
    in
    0.40
     Township
    0.33
    il
    0.31
    t
    0.30
     Studios
    0.29
    on
    0.29
     Twp
    0.28
    sville
    0.27
    َن
    0.27
     तालुक्यातील
    0.27
    Act Density 0.001%

    No Known Activations