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

    Neuronpedia

    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нут
    -0.06
     Tut
    -0.06
     домашних
    -0.06
    non
    -0.06
     BST
    -0.06
    	L
    -0.06
    [self
    -0.06
    ='_
    -0.06
     $.
    -0.06
     incl
    -0.06
    POSITIVE LOGITS
     सम
    0.07
     každ
    0.06
    玉
    0.06
     peque
    0.06
     Peach
    0.06
    />.↵↵
    0.06
    ‌پدیای
    0.06
    救
    0.06
    aisy
    0.06
     Poetry
    0.06
    Act Density 0.009%

    No Known Activations