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

    Neuronpedia

    INDEX
    Explanations

    BMW, crown emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    او
    0.45
    }
    0.43
    }-\
    0.43
     ز
    0.41
    ث
    0.40
    安置
    0.39
    τρ
    0.38
     phrases
    0.38
    cov
    0.37
    lc
    0.37
    POSITIVE LOGITS
     faculté
    0.51
     tuvo
    0.47
    rijk
    0.46
     जियोग्राफी
    0.46
    çada
    0.46
    segaretro
    0.46
     fabriqué
    0.45
    GALAD
    0.45
    xcsche
    0.45
    ScienceStudent
    0.45
    Act Density 0.003%

    No Known Activations