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

    Neuronpedia

    INDEX
    Explanations

    ventilation and safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waters
    -0.07
    ﻧ
    -0.07
    factor
    -0.07
    혈
    -0.07
    ᵥ
    -0.07
    _term
    -0.07
     pent
    -0.06
    いました
    -0.06
    +n
    -0.06
     자리
    -0.06
    POSITIVE LOGITS
     Crosby
    0.08
     Mult
    0.07
    losing
    0.06
     Mia
    0.06
    iding
    0.06
    困难
    0.06
    啟
    0.06
     weekends
    0.06
    0.06
    Lib
    0.06
    Act Density 0.008%

    No Known Activations