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

    Neuronpedia

    INDEX
    Explanations

    no single "best"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actively
    0.41
    VisualStudio
    0.40
    ?\
    0.39
     полной
    0.39
    indsight
    0.38
    閱
    0.37
    itiba
    0.36
    undaki
    0.36
    ovid
    0.36
     полноцен
    0.36
    POSITIVE LOGITS
     универса
    0.39
     dependen
    0.39
    枓
    0.38
     optio
    0.37
     материал
    0.37
    thest
    0.36
     inilah
    0.36
    适用于
    0.36
    あり
    0.35
     Depending
    0.35
    Act Density 0.033%

    No Known Activations