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

    Neuronpedia

    INDEX
    Explanations

    creative works and entertainment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.32
     is
    0.31
     două
    0.27
     کرده
    0.25
    ：
    0.24
    й
    0.24
     è
    0.24
    :<
    0.24
     :
    0.23
     này
    0.23
    POSITIVE LOGITS
    ហ៊
    0.25
    c
    0.24
    inated
    0.24
    }});
    0.24
    })$
    0.23
    rezent
    0.23
    ти
    0.23
    such
    0.23
     وم
    0.23
    sm
    0.22
    Act Density 0.394%

    No Known Activations