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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     역사
    -0.07
     verbess
    -0.07
    
    -0.07
     punitive
    -0.07
     खतर
    -0.06
    Filename
    -0.06
    ระเบ
    -0.06
     fragrance
    -0.06
    .ix
    -0.06
    灵
    -0.06
    POSITIVE LOGITS
    =".$
    0.07
    ><?=$
    0.07
     Group
    0.06
    -'.$
    0.06
     centers
    0.06
     randomized
    0.06
    _WM
    0.06
    \Column
    0.06
    =X
    0.06
     centres
    0.06
    Act Density 0.006%

    No Known Activations