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

    Neuronpedia

    INDEX
    Explanations

    purchase decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    唤
    0.42
     ફક્ત
    0.40
     đây
    0.39
    oulos
    0.38
     VERY
    0.38
    VERY
    0.37
    Very
    0.37
     Ere
    0.37
    Fy
    0.37
     Physics
    0.37
    POSITIVE LOGITS
     security
    0.40
     बुल
    0.40
     terlihat
    0.38
     conte
    0.37
     الأمن
    0.37
    HING
    0.36
     危
    0.36
     cadre
    0.36
     নিরাপত্ত
    0.36
    かわ
    0.35
    Act Density 0.002%

    No Known Activations