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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     criança
    -0.08
    胡同
    -0.07
    颇具
    -0.07
    裉
    -0.07
    攻克
    -0.07
    蘧
    -0.07
    ꕥ
    -0.07
    (mon
    -0.07
     impoverished
    -0.06
    ﻲ
    -0.06
    POSITIVE LOGITS
    shint
    0.08
    istringstream
    0.07
     TSR
    0.07
     recycl
    0.07
    ercial
    0.07
    ivic
    0.07
    ====
    0.07
    玞
    0.07
     Battle
    0.07
     electroly
    0.06
    Act Density 0.050%

    No Known Activations