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

    Neuronpedia

    INDEX
    Explanations

    oxygen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extends
    -0.08
     emphasizes
    -0.08
     ins
    -0.07
     ਵ
    -0.07
    引
    -0.07
     consensus
    -0.07
    適
    -0.07
     ਖ
    -0.07
     highlights
    -0.07
    кін
    -0.07
    POSITIVE LOGITS
    .partner
    0.09
    _partner
    0.09
     partner
    0.09
     partenaire
    0.08
    Facing
    0.08
     parceiro
    0.08
     partenaires
    0.08
    Partner
    0.08
     portrait
    0.08
     partnering
    0.08
    Act Density 0.001%

    No Known Activations