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

    Neuronpedia

    INDEX
    Explanations

    interview-related content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notifies
    0.41
     notifications
    0.38
     uses
    0.37
     hypothesis
    0.37
     অবহিত
    0.37
     সংশোধন
    0.37
     notify
    0.37
     indicates
    0.36
    "\
    0.36
     باستخدام
    0.36
    POSITIVE LOGITS
    Interview
    1.76
     interview
    1.70
     Interview
    1.70
     интервью
    1.70
     entrevista
    1.66
    interview
    1.63
     interviews
    1.62
     entrevistas
    1.58
     Interviews
    1.55
    インタビュー
    1.53
    Act Density 0.029%

    No Known Activations