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

    Neuronpedia

    INDEX
    Explanations

    reduction and oxidation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     */;
    0.91
    נו
    0.90
    IAC
    0.89
    ForRule
    0.88
    셔야
    0.86
     freehold
    0.85
    郓
    0.83
    ILayout
    0.81
    ﾈ
    0.81
    ыска
    0.80
    POSITIVE LOGITS
     oxidize
    1.09
     corro
    1.05
     oxid
    1.02
     hadiah
    1.02
     oksid
    1.02
     elektr
    0.99
    oxidation
    0.99
     oxyd
    0.98
     muere
    0.97
    ﻤ
    0.96
    Act Density 0.026%

    No Known Activations