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

    Neuronpedia

    INDEX
    Explanations

    monarch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     illust
    -0.07
     balancing
    -0.07
     Contribution
    -0.06
     Affairs
    -0.06
     Protective
    -0.06
     Canton
    -0.06
     görün
    -0.06
    Det
    -0.06
    тивного
    -0.06
     lesser
    -0.06
    POSITIVE LOGITS
     monarch
    0.14
     monarchy
    0.12
    (<
    0.07
    archy
    0.07
    arch
    0.07
     shemale
    0.07
    Through
    0.07
    invoke
    0.07
    OWNER
    0.07
    Scene
    0.07
    Act Density 0.002%

    No Known Activations