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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ycin
    -0.07
    .face
    -0.07
    =\'
    -0.06
    回答
    -0.06
    وز
    -0.06
    ').'
    -0.06
    .Fl
    -0.06
    .''
    -0.06
    ày
    -0.06
     Articles
    -0.06
    POSITIVE LOGITS
    landers
    0.06
     шаг
    0.06
    -job
    0.06
    Reason
    0.06
     Winter
    0.06
    hir
    0.06
    OUTPUT
    0.06
     те
    0.06
     přímo
    0.06
     wholly
    0.06
    Act Density 0.013%

    No Known Activations