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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    297
    -0.06
    337
    -0.06
     Kul
    -0.06
    ERSION
    -0.06
     outfile
    -0.06
     appId
    -0.06
     histó
    -0.06
    =}
    -0.06
     정부
    -0.06
    ARIANT
    -0.06
    POSITIVE LOGITS
     podnikatel
    0.07
     установлен
    0.07
    。↵↵↵↵
    0.07
    قيق
    0.07
     تمامی
    0.07
    办公
    0.07
    _n
    0.06
    _Page
    0.06
     lying
    0.06
     m�
    0.06
    Act Density 0.004%

    No Known Activations