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

    Neuronpedia

    INDEX
    Explanations

    speed and expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hão
    0.56
    estern
    0.44
    enal
    0.43
    üd
    0.43
    剥
    0.43
    yd
    0.43
    ม
    0.42
    ympt
    0.42
    ograd
    0.42
    ­
    0.41
    POSITIVE LOGITS
     имя
    0.52
     какой
    0.51
     OXIDES
    0.51
    Andy
    0.50
     basaltes
    0.49
     произведения
    0.48
     коллеги
    0.48
     растения
    0.48
     страницы
    0.48
     счита
    0.48
    Act Density 0.000%

    No Known Activations