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

    Neuronpedia

    INDEX
    Explanations

    Code of Hammurabi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sommes
    -0.08
     Cert
    -0.07
    .lower
    -0.07
    เร
    -0.07
     humility
    -0.07
    prenom
    -0.07
     stimuler
    -0.07
     uncert
    -0.07
    สถาน
    -0.07
     obstacle
    -0.07
    POSITIVE LOGITS
    制定
    0.08
     《
    0.08
     नियम
    0.08
    MAKE
    0.08
    oleč
    0.08
    /Public
    0.08
     kuidas
    0.08
     Instructions
    0.08
    UILD
    0.08
     ألا
    0.08
    Act Density 0.004%

    No Known Activations