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

    Neuronpedia

    INDEX
    Explanations

    hands visible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    solete
    0.75
     가진
    0.65
     поводу
    0.64
    ateau
    0.63
    imir
    0.62
    JlcG
    0.60
    buat
    0.59
    owing
    0.58
     ลอง
    0.57
     putative
    0.57
    POSITIVE LOGITS
    ทุก
    0.77
     reactants
    0.72
     IMMEDI
    0.69
    盥
    0.66
    ใน
    0.66
     COMPLET
    0.66
    ごとに
    0.66
    Repeat
    0.66
     inital
    0.65
    汙
    0.65
    Act Density 0.169%

    No Known Activations