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

    Neuronpedia

    INDEX
    Explanations

    stock trading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vera
    0.42
     trou
    0.41
    isc
    0.40
     intermolecular
    0.39
     Israel
    0.39
     isra
    0.39
     умира
    0.39
     perspici
    0.38
     Interfaith
    0.38
    âne
    0.38
    POSITIVE LOGITS
    Teams
    0.52
    ค่อย
    0.52
    복
    0.51
    Latency
    0.50
    ปล
    0.50
    ט
    0.49
    س
    0.48
    اپ
    0.47
    ש
    0.46
    蒻
    0.46
    Act Density 0.001%

    No Known Activations