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

    Neuronpedia

    INDEX
    Explanations

    Esperanto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lime
    0.40
     বেড়ে
    0.40
    十五章
    0.40
     pregnant
    0.38
    mentor
    0.38
    温
    0.38
    ర్కొ
    0.37
     cryptic
    0.37
    iterranée
    0.37
    दों
    0.36
    POSITIVE LOGITS
     sehari
    0.41
    ทำงาน
    0.40
     Ferd
    0.40
     surrounding
    0.40
     ನಿಮ್ಮ
    0.40
     وفا
    0.39
     Nob
    0.39
     Complaints
    0.38
     ವ್ಯಾ
    0.38
     Ferm
    0.37
    Act Density 0.003%

    No Known Activations