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

    Neuronpedia

    INDEX
    Explanations

    book descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     канди
    -0.07
    nts
    -0.06
     안전
    -0.06
    ै↵
    -0.06
    리고
    -0.06
    Fat
    -0.06
     Hof
    -0.06
    Stick
    -0.06
    이슈
    -0.06
    .ItemStack
    -0.06
    POSITIVE LOGITS
    _Space
    0.07
    ฬ
    0.07
     dej
    0.07
    amous
    0.06
    	me
    0.06
     puls
    0.06
     emissions
    0.06
    bbbb
    0.06
    [L
    0.06
     nick
    0.06
    Act Density 0.019%

    No Known Activations