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

    Neuronpedia

    INDEX
    Explanations

    letting off, items taken, communication skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    answer
    0.44
    stime
    0.41
    6
    0.39
    question
    0.38
    回答
    0.38
     thí
    0.38
    There
    0.38
    Стра
    0.37
    answered
    0.36
    event
    0.35
    POSITIVE LOGITS
     പ്രച
    0.46
    писок
    0.44
     eigenlijk
    0.42
    ╅
    0.41
    მასრულ
    0.41
    컫
    0.41
     እድ
    0.41
    );*/
    0.40
     unsus
    0.40
    ROID
    0.40
    Act Density 0.000%

    No Known Activations