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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kitap
    -0.08
     rab
    -0.08
     Wiener
    -0.07
    -0.07
    normally
    -0.07
     configs
    -0.07
     äußerst
    -0.07
    ._↵↵
    -0.07
    ."""↵↵
    -0.07
    模拟
    -0.07
    POSITIVE LOGITS
    enville
    0.09
     기술
    0.08
     тех
    0.08
     бол
    0.08
     técnica
    0.07
     技
    0.07
    技
    0.07
     jälle
    0.07
     پہ
    0.07
    /App
    0.07
    Act Density 0.109%
    No Known Activations