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

    Neuronpedia

    INDEX
    Explanations

    salutations and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teas
    0.35
    Creative
    0.35
     wond
    0.35
     waven
    0.34
    لیف
    0.34
     Creative
    0.33
     Roboto
    0.33
    sova
    0.33
    웬
    0.33
     በማ
    0.33
    POSITIVE LOGITS
    ানি
    0.44
    ানী
    0.42
     aqui
    0.40
     سرح
    0.39
     доступны
    0.39
     Kyung
    0.38
     aici
    0.38
     повре
    0.38
    auth
    0.38
     финан
    0.38
    Act Density 0.001%

    No Known Activations