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

    Neuronpedia

    INDEX
    Explanations

    fill in blanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বিশ্লেষণ
    0.38
    deling
    0.38
    롭게
    0.38
    一组
    0.37
     गारंटी
    0.34
    perm
    0.34
    বেদন
    0.34
    ге
    0.34
    nge
    0.34
    rimidin
    0.34
    POSITIVE LOGITS
     word
    0.47
     Fill
    0.47
     لفظ
    0.46
    Fill
    0.44
     FILL
    0.44
     crossword
    0.43
     слово
    0.43
     riječ
    0.42
     શબ્
    0.42
     nevez
    0.42
    Act Density 0.057%

    No Known Activations