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

    Neuronpedia

    INDEX
    Explanations

    oxidation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ñas
    -0.08
    ARRANT
    -0.08
    Je
    -0.07
    як
    -0.07
    Le
    -0.07
     ranged
    -0.07
    yš
    -0.07
     hassle
    -0.07
     Freel
    -0.07
     reinc
    -0.07
    POSITIVE LOGITS
     oxidation
    0.16
     oxid
    0.12
    oxid
    0.08
    !",
    0.07
    xit
    0.07
     Formatting
    0.07
    коном
    0.06
     outdated
    0.06
    .OUT
    0.06
     Ott
    0.06
    Act Density 0.006%

    No Known Activations