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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iy
    1.60
    ו
    1.33
    ್ಯ
    1.30
    a
    1.12
    o
    1.09
    it
    1.08
     Hvis
    1.07
    )
    1.05
    ais
    1.04
    ers
    1.02
    POSITIVE LOGITS
    做法
    1.26
    мент
    1.23
    জন
    1.22
     combustibles
    1.21
    AST
    1.19
    ravo
    1.18
     interpolate
    1.18
    न्दावन
    1.17
     spectrometers
    1.16
     undermine
    1.15
    Act Density 0.003%

    No Known Activations