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

    Neuronpedia

    INDEX
    Explanations

    Canadian Millennials, client needs, voting machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ప్రస్తుతం
    0.44
    Przeczytaj
    0.42
     omnichannel
    0.41
    这家
    0.41
    这款
    0.41
    ٹری
    0.40
     ہے
    0.40
    现有
    0.39
     세상
    0.39
    濵
    0.38
    POSITIVE LOGITS
     and
    0.48
     it
    0.46
     El
    0.46
     এবং
    0.46
    h
    0.45
     N
    0.45
     и
    0.44
    eval
    0.44
     sowie
    0.44
    এবং
    0.44
    Act Density 0.007%

    No Known Activations