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

    Neuronpedia

    INDEX
    Explanations

    dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     интерес
    -0.07
     Slut
    -0.07
    ає
    -0.07
    واج
    -0.06
    ム
    -0.06
     Mong
    -0.06
    aned
    -0.06
    caa
    -0.06
    chia
    -0.06
    єв
    -0.06
    POSITIVE LOGITS
     기준
    0.07
    價
    0.07
    φορ
    0.07
     بیشتر
    0.07
    ạm
    0.06
     dân
    0.06
    ++)
    0.06
    连接
    0.06
     hardships
    0.06
    (inputs
    0.06
    Act Density 0.002%

    No Known Activations