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

    Neuronpedia

    INDEX
    Explanations

    phen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hứng
    -0.07
    Case
    -0.07
     Bayesian
    -0.07
    预见
    -0.07
    の方
    -0.07
    ﻕ
    -0.07
    Correct
    -0.07
     behalf
    -0.07
    殿下
    -0.07
     Sext
    -0.06
    POSITIVE LOGITS
    redient
    0.07
    邻居
    0.07
     rit
    0.07
    然后
    0.07
    _low
    0.06
     Interracial
    0.06
    .pipe
    0.06
    uzzer
    0.06
    ᴻ
    0.06
    _ib
    0.06
    Act Density 0.001%

    No Known Activations