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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     способом
    -0.07
    ológ
    -0.07
     carrot
    -0.07
     threadIdx
    -0.07
     clergy
    -0.07
     пы
    -0.07
    939
    -0.07
     rode
    -0.06
    牛
    -0.06
    _plots
    -0.06
    POSITIVE LOGITS
    frm
    0.07
    getActiveSheet
    0.06
     Dean
    0.06
    歳
    0.06
    ден
    0.06
    の
    0.06
    거래가
    0.06
     kata
    0.06
     IP
    0.06
     業
    0.06
    Act Density 0.012%

    No Known Activations