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

    Neuronpedia

    INDEX
    Explanations

    research experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hermosa
    0.50
     embarazada
    0.50
     hermoso
    0.49
    ayev
    0.46
     wundersch
    0.46
     CustB
    0.46
     documentación
    0.45
     ಅತ್ಯ
    0.45
    ampuan
    0.45
     asistente
    0.45
    POSITIVE LOGITS
    ള്ളി
    0.43
    。
    0.42
     بشأن
    0.41
     تع
    0.40
    在
    0.40
    致
    0.39
     جایی
    0.39
    elog
    0.38
    Ow
    0.37
     whiteboard
    0.37
    Act Density 0.005%

    No Known Activations