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

    Neuronpedia

    INDEX
    Explanations

    key concepts and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     from
    0.41
     lamps
    0.41
     traces
    0.36
    方
    0.36
    from
    0.36
     bushes
    0.35
    ্মদ
    0.35
    ächlich
    0.35
     possibles
    0.35
    方を
    0.35
    POSITIVE LOGITS
     特に
    0.50
     especialmente
    0.50
     खासकर
    0.49
     Особенно
    0.48
    ‼️
    0.48
     Especially
    0.48
    특히
    0.48
    Especially
    0.47
    ので
    0.47
    何况
    0.46
    Act Density 0.162%

    No Known Activations