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

    Neuronpedia

    INDEX
    Explanations

    scientific citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出
    -0.07
     congressional
    -0.06
    Deposit
    -0.06
    ometrics
    -0.06
     ва
    -0.06
    UZ
    -0.06
     сест
    -0.06
    contest
    -0.06
    าจารย
    -0.06
     allocator
    -0.06
    POSITIVE LOGITS
    160
    0.07
    -tm
    0.07
     Sau
    0.06
    focus
    0.06
    	MessageBox
    0.06
    [temp
    0.06
    ��
    0.06
     Ре
    0.06
     بندی
    0.06
    .Te
    0.06
    Act Density 0.008%

    No Known Activations