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

    Neuronpedia

    INDEX
    Explanations

    differences between words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সাহেবের
    0.42
    othi
    0.42
    iče
    0.41
    被害
    0.41
    rap
    0.40
    老师
    0.38
     samarbe
    0.37
     awhile
    0.37
    eva
    0.37
     संदेह
    0.37
    POSITIVE LOGITS
     ajoute
    0.49
     submersible
    0.49
     Vulcan
    0.47
     သိ
    0.46
     Alibaba
    0.46
     pluck
    0.46
    を追加
    0.46
     appliquer
    0.46
     tacky
    0.45
     の
    0.45
    Act Density 0.001%

    No Known Activations