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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SER
    -0.07
    籍
    -0.07
    用户
    -0.07
    SCI
    -0.07
    ียง
    -0.07
    asive
    -0.07
    getVar
    -0.06
    .token
    -0.06
    工業
    -0.06
    wares
    -0.06
    POSITIVE LOGITS
     뒤
    0.06
     fol
    0.06
    	rs
    0.06
     Друг
    0.06
     четвер
    0.06
     同
    0.06
     cadastr
    0.06
     outf
    0.06
     produce
    0.06
    decrypt
    0.05
    Act Density 0.000%

    No Known Activations