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

    Neuronpedia

    INDEX
    Explanations

    quarterly trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    并且
    0.64
     बिज़नेस
    0.61
    ޢ
    0.61
    並且
    0.59
    ⺠
    0.57
    ೦
    0.56
     हाँ
    0.54
     ڕ
    0.53
     जाँच
    0.50
     ~
    0.50
    POSITIVE LOGITS
     amid
    0.78
     lawmaker
    0.75
     yüzde
    0.66
     yakni
    0.64
     staffers
    0.64
    －
    0.64
     महज
    0.61
    Amid
    0.60
     ওই
    0.60
     lawmakers
    0.59
    Act Density 0.006%

    No Known Activations