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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conclu
    0.66
     múlti
    0.62
    อนุ
    0.62
    いき
    0.61
    ),]$
    0.61
    る
    0.61
    ন্ড
    0.61
     gustaría
    0.61
     полага
    0.61
     $\{(
    0.61
    POSITIVE LOGITS
     Eastwood
    0.77
    上面的
    0.70
    larda
    0.69
    girl
    0.68
     Jangan
    0.68
     Vào
    0.68
     Show
    0.66
     själv
    0.66
    lendir
    0.66
     Confederate
    0.65
    Act Density 0.031%

    No Known Activations