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

    Neuronpedia

    INDEX
    Explanations

    avoid stealing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cómo
    0.52
     इंस्टाग्राम
    0.52
    instagram
    0.50
    राजस्थान
    0.50
     കമ്മി
    0.50
    פ
    0.49
    鞦
    0.48
    Evento
    0.48
    儁
    0.48
    Ngày
    0.47
    POSITIVE LOGITS
     sites
    0.54
     <
    0.51
    ),
    0.51
     analy
    0.47
    '
    0.47
     measures
    0.47
     Sites
    0.47
    ).
    0.45
     =
    0.45
     konk
    0.44
    Act Density 0.001%

    No Known Activations