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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and formatting marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tak
    -0.07
    Tak
    -0.07
    收录
    -0.07
     ΕΛ
    -0.06
     devout
    -0.06
     хто
    -0.06
     Ltd
    -0.06
    -स
    -0.06
     muž
    -0.06
    Wie
    -0.06
    POSITIVE LOGITS
    homes
    0.06
     ав
    0.06
    !")↵
    0.06
    ��
    0.06
    /text
    0.06
     sobre
    0.06
    -tag
    0.06
    bett
    0.06
    -version
    0.06
    resentation
    0.06
    Act Density 0.002%

    No Known Activations