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

    Neuronpedia

    INDEX
    Explanations

    transition into or onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gespielt
    0.19
     persists
    0.19
     অতঃপর
    0.18
     می‌باشد
    0.17
     ऑर्
    0.17
     før
    0.17
     trembled
    0.17
          
    0.17
     όταν
    0.17
     Ordinance
    0.17
    POSITIVE LOGITS
     into
    0.36
    into
    0.31
     इनटू
    0.27
     onto
    0.26
     vào
    0.26
    Into
    0.23
     ਨੂੰ
    0.22
     را
    0.21
     accordingly
    0.21
    ઓને
    0.21
    Act Density 0.168%

    No Known Activations