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

    Neuronpedia

    INDEX
    Explanations

    starting and beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EB
    0.33
    মো
    0.32
     zwischen
    0.32
     চলেছে
    0.31
     паў
    0.30
     keperluan
    0.30
    สาร
    0.29
    JlcG
    0.29
     tijekom
    0.29
    מש
    0.29
    POSITIVE LOGITS
     afresh
    0.60
    આત
    0.58
     started
    0.55
     Started
    0.55
    started
    0.55
    आती
    0.55
     开始
    0.53
     anew
    0.53
     начал
    0.52
     festivities
    0.51
    Act Density 0.079%

    No Known Activations