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

    Neuronpedia

    INDEX
    Explanations

    root cause analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indoct
    0.88
     unethical
    0.87
     unscrupulous
    0.82
     indoctr
    0.80
     ප්‍රති
    0.80
     परियोजनाओं
    0.78
     thighs
    0.77
    ITH
    0.77
     ඔබට
    0.77
     Selenium
    0.77
    POSITIVE LOGITS
    og
    0.69
     apiece
    0.64
    es
    0.62
    rieved
    0.61
     സി
    0.60
    visional
    0.59
    astanza
    0.59
    リエ
    0.58
     chases
    0.57
     मझ
    0.57
    Act Density 0.013%

    No Known Activations