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

    Neuronpedia

    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    計
    -0.07
     unlimited
    -0.07
     never
    -0.07
     lệ
    -0.06
     násled
    -0.06
    ocrats
    -0.06
     chance
    -0.06
     █
    -0.06
     chilling
    -0.06
    飛
    -0.06
    POSITIVE LOGITS
    Overlap
    0.07
    에서는
    0.07
     SHA
    0.06
    .PIPE
    0.06
    [];
↵
    0.06
     процессе
    0.06
    /shop
    0.06
    Kind
    0.06
    Noise
    0.06
    ...',↵
    0.06
    Act Density 0.022%

    No Known Activations