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

    Neuronpedia

    INDEX
    Explanations

    mergers and acquisitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.90
     sobreviv
    0.86
     estudi
    0.83
     определя
    0.82
    ション
    0.79
    閒
    0.79
     détermin
    0.77
    นั้น
    0.77
    த்தில்
    0.76
    liefer
    0.76
    POSITIVE LOGITS
     จำนวน
    0.91
    ಿಂದ
    0.89
     sajana
    0.87
    পাড়া
    0.86
     جديده
    0.84
    ﾓ
    0.84
     비해
    0.81
     modals
    0.80
    ان
    0.80
    nak
    0.80
    Act Density 0.001%

    No Known Activations