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

    Neuronpedia

    INDEX
    Explanations

    purpose or destination "for"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dyž
    0.82
     જેટ
    0.76
    వాన్ని
    0.74
     keresztül
    0.73
    ीजन
    0.73
    ரிடம்
    0.73
    到的
    0.73
    瞥
    0.71
    évő
    0.69
     السبب
    0.69
    POSITIVE LOGITS
     for
    5.50
     для
    5.09
    for
    4.60
     für
    4.53
     pentru
    4.34
     voor
    4.33
     untuk
    4.29
    สำหรับ
    4.10
    для
    4.02
     för
    3.98
    Act Density 2.175%

    No Known Activations